Generating consistent multi-view images given a text prompt is an essential bridge to generating synthetic 3D assets. In this work, we introduce RapidMV, a novel text-to-multi-view generative model that can produce 32 multi-view synthetic images in just around 5 seconds. In essence, we introduce a novel spatio-angular latent space, where we encode not only the spatial appearance of a single frame, but also the angular viewpoint deviations across multiple frames into a single latent for improved efficiency and multi-view consistency. We achieve effective training of RapidMV by strategically decomposing our training process into multiple steps. We demonstrate that RapidMV outperforms existing methods in terms of consistency and latency, with competitive quality and text-image alignment.

Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework designed to enhance the locality and interaction awareness of CLIP representations. The locality awareness, which involves capturing fine-grained details and the spatial structure of individual objects, is achieved by aggregating the information and spatial priors of adjacent neighborhood patches. The interaction awareness, which involves identifying whether and how a human is interacting with an object, is achieved by capturing the interaction pattern between the human and the object. By infusing locality and interaction awareness into CLIP representations, LAIN captures detailed information about the human-object pairs. Our extensive experiments on existing benchmarks show that LAIN outperforms previous methods in various zero-shot settings, demonstrating the importance of locality and interaction awareness for effective zero-shot HOI detection.

The exponential increase in video content poses significant challenges in terms of efficient navigation, search, and retrieval, thus requiring advanced video summarization techniques. Existing video summarization methods, which heavily rely on visual features and temporal dynamics, often fail to capture the semantics of video content, resulting in incomplete or incoherent summaries. To tackle the challenge, we propose a new video summarization framework that leverages the capabilities of recent Large Language Models (LLMs), expecting that the knowledge learned from massive data enables LLMs to evaluate video frames in a manner that better aligns with diverse semantics and human judgments, effectively addressing the inherent subjectivity in defining keyframes. Our method, dubbed LLM-based Video Summarization (LLMVS), translates video frames into a sequence of captions using a Muti-modal Large Language Model (M-LLM) and then assesses the importance of each frame using an LLM, based on the captions in its local context. These local importance scores are refined through a global attention mechanism in the entire context of video captions, ensuring that our summaries effectively reflect both the details and the overarching narrative. Our experimental results demonstrate the superiority of the proposed method over existing ones in standard benchmarks, highlighting the potential of LLMs in the processing of multimedia content.

We tackle open-vocabulary 3D scene segmentation tasks by introducing a novel data generation pipeline and training framework. Our work targets three essential aspects required for an effective dataset: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale. By leveraging state-of-the-art open-vocabulary image segmentation models and region-aware vision-language models (VLM), we develop an automatic pipeline capable of producing high-quality 3D mask-text pairs. Applying this pipeline to multiple 3D scene datasets, we create Mosaic3D-5.6M, a dataset of more than 30K annotated scenes with 5.6M mask-text pairs - significantly larger than existing datasets. Building on these data, we propose Mosaic3D, a 3D visiual foundation model (3D-VFM) combining a 3D encoder trained with contrastive learning and a lightweight mask decoder for open-vocabulary 3D semantic and instance segmentation. Our approach achieves state-of-the-art results on open-vocabulary 3D semantic and instance segmentation benchmarks including ScanNet200, Matterport3D, and ScanNet++, with ablation studies validating the effectiveness of our large-scale training data. https://nvlabs.github.io/Mosaic3D/

Symmetry plays a vital role in understanding structural patterns, aiding object recognition and scene interpretation. This paper focuses on rotation symmetry, where objects remain unchanged when rotated around a central axis, requiring detection of rotation centers and supporting vertices. Traditional methods relied on hand-crafted feature matching, while recent segmentation models based on convolutional neural networks (CNNs) detect rotation centers but struggle with 3D geometric consistency due to viewpoint distortions. To overcome this, we propose a model that directly predicts rotation centers and vertices in 3D space and projects the results back to 2D while preserving structural integrity. By incorporating a vertex reconstruction stage enforcing 3D geometric priors—such as equal side lengths and interior angles—our model enhances robustness and accuracy. Experiments on the DENDI dataset show superior performance in rotation axis detection and validate the impact of 3D priors through ablation studies.

Generic event boundary detection (GEBD) aims to identify natural boundaries in a video, segmenting it into distinct and meaningful chunks. Despite the inherent subjectivity of event boundaries, previous methods have focused on deterministic predictions, overlooking the diversity of plausible solutions. In this paper, we introduce a novel diffusion-based boundary detection model, dubbed DiffGEBD, that tackles the problem of GEBD from a generative perspective. The proposed model encodes relevant changes across adjacent frames via temporal self-similarity and then iteratively decodes random noise into plausible event boundaries being conditioned on the encoded features. Classifier-free guidance allows the degree of diversity to be controlled in denoising diffusion. In addition, we introduce a new evaluation metric to assess the quality of predictions considering both diversity and fidelity. Experiments show that our method achieves strong performance on two standard benchmarks, Kinetics-GEBD and TAPOS, generating diverse and plausible event boundaries.

Social interactions often emerge from subtle, fine-grained cues such as facial expressions, gaze, and gestures. However, existing methods for social interaction detection overlook such nuanced cues and primarily rely on holistic representations of individuals. Moreover, they directly detect social groups without explicitly modeling the underlying interactions between individuals. These drawbacks limit their ability to capture localized social signals and introduce ambiguity when group configurations should be inferred from social interactions grounded in nuanced cues. In this work, we propose a part-aware bottom-up group reasoning framework for fine-grained social interaction detection. The proposed method infers social groups and their interactions using body part cues and their interpersonal relations. Our model first detects individuals and enhances their features using part-aware cues, and then infers group configuration by associating individuals via similarity-based reasoning, which considers not only spatial relations but also subtle social cues that signal interactions, leading to more accurate group inference. Experiments on the NVI dataset demonstrate that our method outperforms prior methods, achieving the new state of the art, while additional results on the Café dataset further validate its generalizability to group activity understanding.

We address the problem of generalized category discovery (GCD) that aims to partition a partially labeled collection of images; only a small part of the collection is labeled and the total number of target classes is unknown. To address this generalized image clustering problem, we revisit the mean-shift algorithm, i.e., a classic, powerful technique for mode seeking, and incorporate it into a contrastive learning framework. The proposed method, dubbed Contrastive Mean-Shift (CMS) learning, trains an embedding network to produce representations with better clustering properties by an iterative process of mean shift and contrastive update. Experiments demonstrate that our method, both in settings with and without the total number of clusters being known, achieves state-of-the-art performance on six public GCD benchmarks without bells and whistles.

Leveraging multi-view diffusion models as priors for 3D optimization have alleviated the problem of 3D consistency, e.g., the Janus face problem or the content drift problem, in zero-shot text-to-3D models. However, the 3D geomet-ric fidelity of the output remains an unresolved issue; albeit the rendered 2D views are realistic, the underlying geom-etry may contain errors such as unreasonable concavities. In this work, we propose CorrespondentDream, an effective method to leverage annotation-free, cross-view corre- spondences yielded from the diffusion U-Net to provide additional 3D prior to the NeRF optimization process. We find that these correspondences are strongly consistent with hu-man perception, and by adopting it in our loss design, we are able to produce NeRF models with geometries that are more coherent with common sense, e.g., more smoothed ob-ject surface, yielding higher 3D fidelity. We demonstrate the efficacy of our approach through various comparative qualitative results and a solid user study.

We introduce a new attention mechanism, dubbed structural self-attention (StructSA), that leverages rich correlation patterns naturally emerging in key-query interactions of attention. StructSA generates attention maps by recog-nizing space-time structures of key-query correlations via convolution and uses them to dynamically aggregate lo-cal contexts of value features. This effectively leverages rich structural patterns in images and videos such as scene layouts, object motion, and inter-object relations. Using StructSA as a main building block, we develop the structural vision transformer (StructViT) and evaluate its effective-ness on both image and video classification tasks, achieving state-of-the-art results on ImageNet-I K, Kinetics-400, Something-Something VI & V2, Diving-48, and FineGym.

This paper addresses the task of video question answering (videoQA) via a decomposed multi-stage, modular rea-soning framework. Previous modular methods have shown promise with a single planning stage ungrounded in visual content. However, through a simple and effective base-line, we find that such systems can lead to brittle behavior in practice for challenging videoQA settings. Thus, unlike traditional single-stage planning methods, we propose a multi-stage system consisting of an event parser, a grounding stage, and a final reasoning stage in conjunction with an external memory. All stages are training-free, and performed using few-shot prompting of large models, creating interpretable intermediate outputs at each stage. By decomposing the underlying planning and task complexity, our method, MoReVQA, improves over prior work on stan-dard videoQA benchmarks (NExT-QA, iVQA, EgoSchema, ActivityNet-QA) with state-of-the-art results, and extensions to related tasks (grounded videoQA, paragraph captioning).

Establishing accurate 3D correspondences between shapes stands as a pivotal challenge with profound implications for computer vision and robotics. However, existing self-supervised methods for this problem assume perfect input shape alignment, restricting their real-world applicability. In this work, we introduce a novel self-supervised Rotation-Invariant 3D correspondence learner with local Shape Transform, dubbed RIST, that learns to establish dense correspondences between shapes even under challenging intra-class variations and arbitrary orientations. Specifically, RIST learns to dynamically formulate an SO(3) -invariant local shape transform for each point, which maps the SO(3)-equivariant global shape descriptor of the input shape to a local shape descriptor. These local shape descriptors are provided as inputs to our decoder to facilitate point cloud self- and cross-reconstruction. Our proposed self-supervised training pipeline encourages semantically corresponding points from different shapes to be mapped to similar local shape descriptors, enabling RIST to establish dense point-wise correspondences. RIST demonstrates state-of-the-art performances on 3D part label transfer and semantic keypoint transfer given arbitrarily rotated point cloud pairs of the same category, outperforming existing methods by significant margins.

Sorting is a fundamental operation of all computer systems, having been a long-standing significant research topic. Beyond the problem formulation of traditional sorting algorithms, we consider sorting problems for more abstract yet expressive inputs, e.g., multi-digit images and image fragments, through a neural sorting network. To learn a mapping from a high-dimensional input to an ordinal variable, the differentiability of sorting networks needs to be guaranteed. In this paper we define a softening error by a differentiable swap function, and develop an error-free swap function that holds a non-decreasing condition and differentiability. Furthermore, a permutation-equivariant Transformer network with multi-head attention is adopted to capture dependency between given inputs and also leverage its model capacity with self-attention. Experiments on diverse sorting benchmarks show that our methods perform better than or comparable to baseline methods.

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and compute. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://nahyuklee.github.io/pmtr

Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential complementarity, these two problems have been investigated as separate and distinct tasks. In this work, we tackle these two problems, action segmentation, and action anticipation, jointly using a unified diffusion model dubbed ActFusion. The key idea to unification is to train the model to effectively handle both visible and invisible parts of the sequence in an integrated manner; the visible part is for temporal segmentation, and the invisible part is for future anticipation. To this end, we introduce a new anticipative masking strategy during training in which a late part of the video frames is masked as invisible, and learnable tokens replace these frames to learn to predict the invisible future. Experimental results demonstrate the bi-directional benefits between action segmentation and anticipation. ActFusion achieves the state-of-the-art performance across the standard benchmarks of 50 Salads, Breakfast, and GTEA, outperforming task-specific models in both of the two tasks with a single unified model through joint learning.

Determining the 3D orientations of an object in an image, known as single-image pose estimation, is a crucial task in 3D vision applications. Existing methods typically learn 3D rotations parametrized in the spatial domain using Euler angles or quaternions, but these representations often introduce discontinuities and singularities. SO(3)-equivariant networks enable the structured capture of pose patterns with data-efficient learning, but the parametrizations in spatial domain are incompatible with their architecture, particularly spherical CNNs, which operate in the frequency domain to enhance computational efficiency. To overcome these issues, we propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression, aligning with the operations of spherical CNNs. Our SO(3)-equivariant pose harmonics predictor overcomes the limitations of spatial parameterizations, ensuring consistent pose estimation under arbitrary rotations. Trained with a frequency-domain regression loss, our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+, with significant improvements in accuracy, robustness, and data efficiency.

Recent studies show that leveraging the match-wise relationships within the 4D correlation map yields significant improvements in establishing semantic correspondences - but at the cost of increased computation and latency. In this work, we focus on the aspect that the performance improvements of recent methods can also largely be attributed to the usage of multi-scale correlation maps, which hold various information ranging from low-level geometric cues to high-level semantic contexts. To this end, we propose HCCNet, an efficient yet effective semantic matching method which exploits the full potential of multi-scale correlation maps, while eschewing the reliance on expensive matchwise relationship mining on the 4D correlation map. Specifically, HCCNet performs feature slicing on the bottleneck features to yield a richer set of intermediate features, which are used to construct a hypercolumn correlation. HCCNet can consequently establish semantic correspondences in an effective manner by reducing the volume of conventional high-dimensional convolution or self-attention operations to efficient point-wise convolutions. HCCNet demonstrates state-of-the-art or competitive performances on the standard benchmarks of semantic matching, while incurring a notably lower latency and computation overhead compared to the existing SoTA methods.

Existing datasets for semantic correspondence are often limited in terms of both the amount of labeled data and diversity of labeled keypoints due to the tremendous cost of manual correspondence labeling. To address this issue, we propose the first self-supervised learning framework that utilizes a large amount of web videos collected and annotated fully automatically. Our main motivation is that smooth changes between consecutive video frames allow to build accurate space-time correspondences with no human intervention. Hence, we establish space-time correspondences within each web video and leverage them for deriving pseudo correspondence labels between two distant frames of the video. In addition, we present a dedicated training strategy that facilitates stable training using web videos with such pseudo labels. Our experiments on public benchmarks demonstrated that the proposed method surpasses existing self-supervised learning models and that our self-supervised learning as pretraining for supervised learning improves performance substantially. Our codebase for web video crawling and pseudo label generation will be released public to promote future research.

Optical flows play an integral role for a variety of motion-related tasks such as action recognition, object segmentation, and tracking in videos. While state-of-the-art optical flow methods heavily rely on learning, the learned optical flow methods significantly degrade when applied to different domains, and the training datasets are very limited due to the extreme cost of flow-level annotation. To tackle the issue, we introduce a domain adaptation technique for optical flow estimation. Our method extracts diverse style statistics of the target domain and use them in training to generate synthetic features from the source features, which contain the contents of the source but the style of the target. We also impose motion consistency between the synthetic target and the source and deploy adversarial learning at the flow prediction to encourage domain-invariant features. Experimental results show that the proposed method achieves substantial and consistent improvements in different domain adaptation scenarios on VKITTI 2, Sintel, and KITTI 2015 benchmarks.

Scene graph generation aims to construct a semantic graph structure from an image such that its nodes and edges respectively represent objects and their relationships. One of the major challenges for the task lies in the presence of distracting objects and relationships in images; contextual reasoning is strongly distracted by irrelevant objects or backgrounds and, more importantly, a vast number of irrelevant candidate relations. To tackle the issue, we propose the Selective Quad Attention Network (SQUAT) that learns to select relevant object pairs and disambiguate them via diverse contextual interactions. SQUAT consists of two main components: edge selection and quad attention. The edge selection module selects relevant object pairs, i.e., edges in the scene graph, which helps contextual reasoning, and the quad attention module then updates the edge features using both edge-to-node and edge-to-edge cross-attentions to capture contextual information between objects and object pairs. Experiments demonstrate the strong performance and robustness of SQUAT, achieving the state of the art on the Visual Genome and Open Images v6 benchmarks.

Temporal Action Localization (TAL) methods typically operate on top of feature sequences from a frozen snippet encoder that is pretrained with the Trimmed Action Classification (TAC) tasks, resulting in a task discrepancy problem. While existing TAL methods mitigate this issue either by re-training the encoder with a pretext task or by end-to-end fine-tuning, they commonly require an overload of high memory and computation. In this work, we introduce Soft-Landing (SoLa) strategy, an efficient yet effective framework to bridge the transferability gap between the pretrained encoder and the downstream tasks by incorporating a light-weight neural network, i.e., a SoLa module, on top of the frozen encoder. We also propose an unsupervised training scheme for the SoLa module; it learns with inter-frame Similarity Matching that uses the frame interval as its supervisory signal, eliminating the need for temporal annotations. Experimental evaluation on various benchmarks for downstream TAL tasks shows that our method effectively alleviates the task discrepancy problem with remarkable computational efficiency.

We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed method takes token representations from the self-supervised ViT and leverages their correlations, via selfattention, to produce classification and segmentation predictions through separate task heads. Our model is able to effectively learn to perform classification and segmentation in the absence of pixel-level labels during training, using only image-level labels. To do this it uses attention maps, created from tokens generated by the self-supervised ViT backbone, as pixel-level pseudo-labels. We also explore a practical setup with “mixed” supervision, where a small number of training images contains ground-truth pixel-level labels and the remaining images have only image-level labels. For this mixed setup, we propose to improve the pseudo-labels using a pseudo-label enhancer that was trained using the available ground-truth pixel-level labels. Experiments on Pascal-5iand COCO-20idemonstrate significant performance gains in a variety of supervision settings, and in particular when little-to-no pixel-level labels are available.

Recent state-of-the-art methods for HOI detection typically build on transformer architectures with two decoder branches, one for human-object pair detection and the other for interaction classification. Such disentangled transformers, however, may suffer from insufficient context exchange between the branches and lead to a lack of context information for relational reasoning, which is critical in discovering HOI instances. In this work, we propose the multiplex relation network (MUREN) that performs rich context exchange between three decoder branches using unary, pair-wise, and ternary relations of human, object, and interaction tokens. The proposed method learns comprehensive relational contexts for discovering HOI instances, achieving state-of-the-art performance on two standard benchmarks for HOI detection, HICO-DET and V-COCO.

Despite recent advances in implicit neural representations (INRs), it remains challenging for a coordinate-based multi-layer perceptron (MLP) of INRs to learn a common representation across data instances and generalize it for unseen instances. In this work, we introduce a simple yet effective framework for generalizable INRs that enables a coordinate-based MLP to represent complex data instances by modulating only a small set of weights in an early MLP layer as an instance pattern composer; the remaining MLP weights learn pattern composition rules for common representations across instances. Our generalizable INR frame-work is fully compatible with existing meta-learning and hypernetworks in learning to predict the modulated weight for unseen instances. Extensive experiments demonstrate that our method achieves high performance on a wide range of domains such as an audio, image, and 3D object, while the ablation study validates our weight modulation.

Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to extract discriminative rotation-invariant descriptors using group-equivariant CNNs. Thanks to employing group-equivariant CNNs, our method effectively learns to obtain rotation-equivariant features and their orientations explicitly, without having to perform sophisticated data augmentations. The resultant features and their orientations are further processed by group aligning, a novel invariant mapping technique that shifts the group-equivariant features by their orientations along the group dimension. Our group aligning technique achieves rotation-invariance without any collapse of the group dimension and thus eschews loss of discriminability. The proposed method is trained end-to-end in a self-supervised manner, where we use an orientation alignment loss for the orientation estimation and a contrastive descriptor loss for robust local descriptors to geometric/photometric variations. Our method demonstrates state-of-the-art matching accuracy among existing rotation-invariant descriptors under varying rotation and also shows competitive results when transferred to the task of keypoint matching and camera pose estimation.

Learning to predict reliable characteristic orientations of 3D point clouds is an important yet challenging problem, as different point clouds of the same class may have largely varying appearances. In this work, we introduce a novel method to decouple the shape geometry and semantics of the input point cloud to achieve both stability and consistency. The proposed method integrates shape-geometry-based SO(3)-equivariant learning and shape-semantics-based SO(3)-invariant residual learning, where a final characteristic orientation is obtained by calibrating an SO(3)-equivariant orientation hypothesis using an SO(3)-invariant residual rotation. In experiments, the proposed method not only demonstrates superior stability and consistency but also exhibits state-of-the-art performances when applied to point cloud part segmentation, given randomly rotated inputs.

Sequence prediction on temporal data requires the ability to understand compositional structures of multi-level semantics beyond individual and contextual properties of parts. The task of temporal action segmentation remains challenging for the reason, aiming at translating an untrimmed activity video into a sequence of action segments. This paper addresses the problem by introducing an effective activity grammar to guide neural predictions for temporal action segmentation. We propose a novel grammar induction algorithm, dubbed KARI, that extracts a powerful context-free grammar from action sequence data. We also develop an efficient generalized parser, dubbed BEP, that transforms frame-level probability distributions into a reliable sequence of actions according to the induced grammar with recursive rules. Our approach can be combined with any neural network for temporal action segmentation to enhance the sequence prediction and discover its compositional structure. Experimental results demonstrate that our method significantly improves temporal action segmentation in terms of both performance and interpretability on two standard benchmarks, Breakfast and 50 Salads.

Generalizable implicit neural representation (INR) enables a single continuous function, i.e., a coordinate-based neural network, to represent multiple data instances by modulating its weights or intermediate features using latent codes. However, the expressive power of the state-of-the-art modulation is limited due to its inability to localize and capture fine-grained details of data entities such as specific pixels and rays. To address this issue, we propose a novel framework for generalizable INR that combines a transformer encoder with a locality-aware INR decoder. The transformer encoder predicts a set of latent tokens from a data instance to encode local information into each latent token. The locality-aware INR decoder extracts a modulation vector by selectively aggregating the latent tokens via cross-attention for a coordinate input and then predicts the output by progressively decoding with coarse-to-fine modulation through multiple frequency bandwidths. The selective token aggregation and the multi-band feature modulation enable us to learn locality-aware representation in spatial and spectral aspects, respectively. Our framework significantly outperforms previous generalizable INRs and validates the usefulness of the locality-aware latents for downstream tasks such as image generation.

Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this work we introduce a Hough transform perspective on convolutional matching and propose an effective geometric matching algorithm, dubbed Convolutional Hough Matching (CHM). The method distributes similarities of candidate matches over a geometric transformation space and evaluates them in a convolutional manner. We cast it into a trainable neural layer with a semi-isotropic high-dimensional kernel, which learns non-rigid matching with a small number of interpretable parameters. To further improve the efficiency of high-dimensional voting, we also propose to use an efficient kernel decomposition with center-pivot neighbors, which significantly sparsifies the proposed semi-isotropic kernels without performance degradation. To validate the proposed techniques, we develop the neural network with CHM layers that perform convolutional matching in the space of translation and scaling. Our method sets a new state of the art on standard benchmarks for semantic visual correspondence, proving its strong robustness to challenging intra-class variations.

As autonomous driving research has actively pro-gressed, software for autonomous vehicles and embedded systems such as Apollo and AutoWare have also been developed, providing a complete set of self-driving modules, including perception, localization and mapping, path planning, prediction, decision making, and control. Most of the researchers currently use these software programs, but many researchers have also studied autonomous driving based on the middleware software termed robot operating system (ROS) before such software was released, especially in academia. Accordingly, we intend to develop ROS-based unmanned RC car equipped with autonomous driving sensors such as LiDAR, radar, VIS/IR cameras, GPS, and IMUs that can provide ROS-based datasets to researchers studying self-driving cars and robots using ROS. In addition, unlike conventional datasets, we acquire dataset not only on road but also pedestrian paths that can be used in both vehicles and robots and provides extreme environmental datasets such as snowfall environments. In this sense, the ROS dataset we created will be helpful to researchers studying autonomous vehicles and robots by using ROS.

The task of predicting future actions from a video is crucial for a real-world agent interacting with others. When anticipating actions in the distant future, we humans typically consider long-term relations over the whole sequence of actions, i.e., not only observed actions in the past but also potential actions in the future. In a similar spirit, we propose an end-to-end attention model for action anticipation, dubbed Future Transformer (FUTR), that leverages global attention over all input frames and output tokens to predict a minutes-long sequence of future actions. Unlike the previous autoregressive models, the proposed method learns to predict the whole sequence of future actions in parallel decoding, enabling more accurate and fast inference for long-term anticipation. We evaluate our method on two standard benchmarks for long-term action anticipation, Breakfast and 50 Salads, achieving state-of-the-art results.

We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two conventional few-shot learning problems, few-shot classification and segmentation. FS-CS generalizes them to more realistic episodes with arbitrary image pairs, where each target class may or may not be present in the query. To address the task, we propose the integrative few-shot learning (iFSL) framework for FS-CS, which trains a learner to construct class-wise foreground maps for multi-label classification and pixel-wise segmentation. We also develop an effective iFSL model, attentive squeeze network (ASNet), that leverages deep semantic correlation and global self-attention to produce reliable foreground maps. In experiments, the proposed method shows promising performance on the FS-CS task and also achieves the state of the art on standard few-shot segmentation benchmarks.

We present a novel self-taught framework for unsuper-vised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted relations as pseudo labels. At the heart of our framework lies an algorithm that investigates contexts of data on the embedding space to predict their class-equivalence relations as pseudo labels. The algorithm enables efficient end-to-end training since it demands no off-the-shelf module for pseudo labeling. Also, the class-equivalence relations provide rich supervisory signals for learning an embedding space. On standard benchmarks for metric learning, it clearly outperforms existing unsupervised learning methods and sometimes even beats supervised learning models using the same backbone network. It is also applied to semi-supervised metric learning as a way of exploiting additional unlabeled data, and achieves the state of the art by boosting performance of supervised learning substantially.

Group activity recognition is the task of understanding the activity conducted by a group of people as a whole in a multiperson video. Existing models for this task are often impractical in that they demand ground-truth bounding box labels of actors even in testing or rely on off-the-shelf object detectors. Motivated by this, we propose a novel model for group activity recognition that depends neither on bounding box labels nor on object detector. Our model based on Transformer localizes and encodes partial contexts of a group activity by leveraging the attention mechanism, and represents a video clip as a set of partial context embeddings. The embedding vectors are then aggregated to form a single group representation that reflects the entire context of an activity while capturing temporal evolution of each partial context. Our method achieves outstanding performance on two benchmarks, Volleyball and NBA datasets, surpassing not only the state of the art trained with the same level of supervision, but also some of existing models relying on stronger supervision.

Establishing correspondences between images remains a challenging task, especially under large appearance changes due to different viewpoints or intra-class variations. In this work, we introduce a strong semantic image matching learner, dubbed TransforMatcher, which builds on the success of transformer networks in vision domains. Un-like existing convolution- or attention-based schemes for correspondence, TransforMatcher performs global match-to-match attention for precise match localization and dynamic refinement. To handle a large number of matches in a dense correlation map, we develop a light-weight attention architecture to consider the global match-to-match interactions. We also propose to utilize a multi-channel correlation map for refinement, treating the multi-level scores as features instead of a single score to fully exploit the richer layer-wise semantics. In experiments, TransforMatcher sets a new state of the art on SPair-71k while performing on par with existing SOTA methods on the PF-PASCAL dataset.

Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based methods for keypoint detection rely on standard translation-equivariant CNNs but often fail to detect reliable keypoints against geometric variations. To learn to detect robust oriented keypoints, we introduce a self-supervised learning framework using rotation-equivariant CNNs. We propose a dense orientation alignment loss by an image pair generated by synthetic transformations for training a histogram-based orientation map. Our method outperforms the previous methods on an image matching benchmark and a camera pose estimation benchmark.

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider long-range interactions of codes. However, we postulate that previous VQ cannot shorten the code sequence and generate high-fidelity images together in terms of the rate-distortion trade-off. In this study, we propose the two-stage framework, which consists of Residual-Quantized VAE (RQ-VAE) and RQ-Transformer, to effectively generate high-resolution images. Given a fixed codebook size, RQ-VAE can precisely approximate a feature map of an image and represent the image as a stacked map of discrete codes. Then, RQ-Transformer learns to predict the quantized feature vector at the next position by predicting the next stack of codes. Thanks to the precise approximation of RQ-VAE, we can represent a$256\times 256$image as$8\times 8$resolution of the feature map, and RQ-Transformer can efficiently reduce the computational costs. Consequently, our framework out-performs the existing AR models on various benchmarks of unconditional and conditional image generation. Our approach also has a significantly faster sampling speed than previous AR models to generate high-quality images.

The recent success of neural networks enables a better interpretation of 3D point clouds, but processing a large-scale 3D scene remains a challenging problem. Most current approaches divide a large-scale scene into small regions and combine the local predictions together. However, this scheme inevitably involves additional stages for pre- and post-processing and may also degrade the final output due to predictions in a local perspective. This paper introduces Fast Point Transformer that consists of a new lightweight self-attention layer. Our approach encodes continuous 3D coordinates, and the voxel hashing-based architecture boosts computational efficiency. The proposed method is demonstrated with 3D semantic segmentation and 3D detection. The accuracy of our approach is competitive to the best voxel-based method, and our network achieves 129 times faster inference time than the state-of-the-art, Point Transformer, with a reasonable accuracy trade-off in 3D semantic segmentation on S3DIS dataset.

The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation. The proposed network is built end-to-end with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.

Private inference (PI) enables inferences directly on cryptographically secure data. While promising to address many privacy issues, it has seen limited use due to extreme runtimes. Unlike plaintext inference, where latency is dominated by FLOPs, in PI non-linear functions (namely ReLU) are the bottleneck. Thus, practical PI demands novel ReLU-aware optimizations. To reduce PI latency we propose a gradient-based algorithm that selectively linearizes ReLUs while maintaining prediction accuracy. We evaluate our algorithm on several standard PI benchmarks. The results demonstrate up to $4.25%$ more accuracy (iso-ReLU count at 50K) or $2.2\times$ less latency (iso-accuracy at 70%) than the current state of the art and advance the Pareto frontier across the latency-accuracy space. To complement empirical results, we present a “no free lunch" theorem that sheds light on how and when network linearization is possible while maintaining prediction accuracy.

Assembling parts into an object is a combinatorial problem that arises in a variety of contexts in the real world and involves numerous applications in science and engineering. Previous related work tackles limited cases with identical unit parts or jigsaw-style parts of textured shapes, which greatly mitigate combinatorial challenges of the problem. In this work, we introduce the more challenging problem of shape assembly, which involves textureless fragments of arbitrary shapes with indistinctive junctions, and then propose a learning-based approach to solving it. We demonstrate the effectiveness on shape assembly tasks with various scenarios, including the ones with abnormal fragments (e.g., missing and distorted), the different number of fragments, and different rotation discretization.

Collision avoidance in emergency situations is a crucial and challenging task in motion planning for autonomous vehicles. Especially in the field of optimization-based planning using nonlinear model predictive control, many efforts to achieve real-time performance are still ongoing. Among various approaches, the iterative linear quadratic regulator (iLQR) is known as an efficient means of nonlinear optimization. Additionally, parallel computing architectures, such as GPUs, are more widely applied in autonomous vehicles. In this paper, we propose 1) a parallel computing framework for iLQR with input constraints considering the characteristics of the problem and 2) a proper environmental formulation that can be covered with single-precision floating-point computation of the GPU. The GPU-accelerated framework was tested on a real-time simulation-in-the-loop system using CarMaker and ROS at a 20 Hz sampling rate on a low-performance mobile computer and was compared against the same framework realized with a CPU.

The recent progress in implicit 3D representation, i.e., Neural Radiance Fields (NeRFs), has made accurate and photorealistic 3D reconstruction possible in a differentiable manner. This new representation can effectively convey the information of hundreds of high-resolution images in one compact format and allows photorealistic synthesis of novel views. In this work, using the variant of NeRF called Plenoxels, we create the first large-scale radiance fields datasets for perception tasks, called the PeRFception, which consists of two parts that incorporate both object-centric and scene-centric scans for classification and segmentation. It shows a significant memory compression rate (96.4\%) from the original dataset, while containing both 2D and 3D information in a unified form. We construct the classification and segmentation models that directly take this radiance fields format as input and also propose a novel augmentation technique to avoid overfitting on backgrounds of images. The code and data are publicly available in "https://postech-cvlab.github.io/PeRFception/".

Although autoregressive models have achieved promising results on image generation, their unidirectional generation process prevents the resultant images from fully reflecting global contexts. To address the issue, we propose an effective image generation framework of \emph{Draft-and-Revise} with \emph{Contextual RQ-transformer} to consider global contexts during the generation process. As a generalized VQ-VAE, RQ-VAE first represents a high-resolution image as a sequence of discrete code stacks. After code stacks in the sequence are randomly masked, Contextual RQ-Transformer is trained to infill the masked code stacks based on the unmasked contexts of the image. Then, we propose the two-phase decoding, Draft-and-Revise, for Contextual RQ-Transformer to generates an image, while fully exploiting the global contexts of the image during the generation process. Specifically. in the \emph{draft} phase, our model first focuses on generating diverse images despite rather low quality. Then, in the \emph{revise} phase, the model iteratively improves the quality of images, while preserving the global contexts of generated images. In experiments, our method achieves state-of-the-art results on conditional image generation. We also validate that the Draft-and-Revise decoding can achieve high performance by effectively controlling the quality-diversity trade-off in image generation.

Human vision possesses a special type of visual processing systems called peripheral vision. Partitioning the entire visual field into multiple contour regions based on the distance to the center of our gaze, the peripheral vision provides us the ability to perceive various visual features at different regions. In this work, we take a biologically inspired approach and explore to model peripheral vision in deep neural networks for visual recognition. We propose to incorporate peripheral position encoding to the multi-head self-attention layers to let the network learn to partition the visual field into diverse peripheral regions given training data. We evaluate the proposed network, dubbed PerViT, on ImageNet-1K and systematically investigate the inner workings of the model for machine perception, showing that the network learns to perceive visual data similarly to the way that human vision does. The performance improvements in image classification over the baselines across different model sizes demonstrate the efficacy of the proposed method.

Bayesian optimization is a popular method for solving the problem of global optimization of an expensive-to-evaluate black-box function. It relies on a probabilistic surrogate model of the objective function, upon which an acquisition function is built to determine where next to evaluate the objective function. In general, Bayesian optimization with Gaussian process regression operates on a continuous space. When input variables are categorical or discrete, an extra care is needed. A common approach is to use one-hot encoded or Boolean representation for categorical variables which might yield a combinatorial explosion problem. In this paper we present a method for Bayesian optimization in a combinatorial space, which can operate well in a large combinatorial space. The main idea is to use a random mapping which embeds the combinatorial space into a convex polytope in a continuous space, on which all essential process is performed to determine a solution to the black-box optimization in the combinatorial space. We describe our combinatorial Bayesian optimization algorithm and present its regret analysis. Numerical experiments demonstrate that our method shows satisfactory performance compared to existing methods.

Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. In this paper, we propose a pair-based SSDA method that adapts a model to the target domain using self-distillation with sample pairs. Each sample pair is composed of a teacher sample from a labeled dataset (i.e., source or labeled target) and its student sample from an unlabeled dataset (i.e., unlabeled target). Our method generates an assistant feature by transferring an intermediate style between the teacher and the student, and then train the model by minimizing the output discrepancy between the student and the assistant. During training, the assistants gradually bridge the discrepancy between the two domains, thus allowing the student to easily learn from the teacher. Experimental evaluation on standard benchmarks shows that our method effectively minimizes both the inter-domain and intra-domain discrepancies, thus achieving significant improvements over recent methods.

This paper presents a novel method for embedding transfer, a task of transferring knowledge of a learned embedding model to another. Our method exploits pairwise similarities between samples in the source embedding space as the knowledge, and transfers them through a loss used for learning target embedding models. To this end, we design a new loss called relaxed contrastive loss, which employs the pairwise similarities as relaxed labels for intersample relations. Our loss provides a rich supervisory signal beyond class equivalence, enables more important pairs to contribute more to training, and imposes no restriction on manifolds of target embedding spaces. Experiments on metric learning benchmarks demonstrate that our method largely improves performance, or reduces sizes and output dimensions of target models effectively. We further show that it can be also used to enhance quality of self-supervised representation and performance of classification models. In all the experiments, our method clearly outperforms existing embedding transfer techniques.

Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this work we introduce a Hough transform perspective on convolutional matching and propose an effective geometric matching algorithm, dubbed Convolutional Hough Matching (CHM). The method distributes similarities of candidate matches over a geometric transformation space and evaluate them in a convolutional manner. We cast it into a trainable neural layer with a semi-isotropic high-dimensional kernel, which learns non-rigid matching with a small number of interpretable parameters. To validate the effect, we develop the neural network with CHM layers that perform convolutional matching in the space of translation and scaling. Our method sets a new state of the art on standard benchmarks for semantic visual correspondence, proving its strong robustness to challenging intra-class variations.

In this work, we propose a camera self-calibration algorithm for generic cameras with arbitrary non-linear distortions. We jointly learn the geometry of the scene and the accurate camera parameters without any calibration objects. Our camera model consists of a pinhole model, a fourth order radial distortion, and a generic noise model that can learn arbitrary non-linear camera distortions. While traditional self-calibration algorithms mostly rely on geometric constraints, we additionally incorporate photometric consistency. This requires learning the geometry of the scene, and we use Neural Radiance Fields (NeRF). We also propose a new geometric loss function, viz., projected ray distance loss, to incorporate geometric consistency for complex non-linear camera models. We validate our approach on standard real image datasets and demonstrate that our model can learn the camera intrinsics and extrinsics (pose) from scratch without COLMAP initialization. Also, we show that learning accurate camera models in a differentiable manner allows us to improve PSNR over baselines. Our module is an easy-to-use plugin that can be applied to NeRF variants to improve performance. The code and data are currently available at https://github.com/POSTECH-CVLab/SCNeRF

We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective. Our method lever-ages relational patterns within and between images via self-correlational representation (SCR) and cross-correlational attention (CCA). Within each image, the SCR module transforms a base feature map into a self-correlation tensor and learns to extract structural patterns from the tensor. Between the images, the CCA module computes cross-correlation between two image representations and learns to produce co-attention between them. Our Relational Embedding Network (RENet) combines the two relational modules to learn relational embedding in an end-to-end manner. In experimental evaluation, it achieves consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmarks of miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS.

Spatio-temporal convolution often fails to learn motion dynamics in videos and thus an effective motion representation is required for video understanding in the wild. In this paper, we propose a rich and robust motion representation based on spatio-temporal self-similarity (STSS). Given a sequence of frames, STSS represents each local region as similarities to its neighbors in space and time. By converting appearance features into relational values, it enables the learner to better recognize structural patterns in space and time. We leverage the whole volume of STSS and let our model learn to extract an effective motion representation from it. The proposed neural block, dubbed SELFY, can be easily inserted into neural architectures and trained end-to-end without additional supervision. With a sufficient volume of the neighborhood in space and time, it effectively captures long-term interaction and fast motion in the video, leading to robust action recognition. Our experimental analysis demonstrates its superiority over previous methods for motion modeling as well as its complementarity to spatio-temporal features from direct convolution. On the standard action recognition benchmarks, Something-Something-V1 & V2, Diving-48, and FineGym, the proposed method achieves the state-of-the-art results.

Point cloud registration is the task of estimating the rigid transformation that aligns a pair of point cloud fragments. We present an efficient and robust framework for pairwise registration of real-world 3D scans, leveraging Hough voting in the 6D transformation parameter space. First, deep geometric features are extracted from a point cloud pair to compute putative correspondences. We then construct a set of triplets of correspondences to cast votes on the 6D Hough space, representing the transformation parameters in sparse tensors. Next, a fully convolutional refinement module is applied to refine the noisy votes. Finally, we identify the consensus among the correspondences from the Hough space, which we use to predict our final transformation parameters. Our method outperforms state-of-the-art methods on 3DMatch and 3DLoMatch benchmarks while achieving comparable performance on KITTI odometry dataset. We further demonstrate the generalizability of our approach by setting a new state-of-the-art on ICL-NUIM dataset, where we integrate our module into a multi-way registration pipeline.

Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task requires to understand diverse levels of visual cues and analyze fine-grained correspondence relations between the query and the support images. To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions. It extracts diverse features from different levels of intermediate convolutional layers and constructs a collection of 4D correlation tensors, i.e., hypercorrelations. Using efficient center-pivot 4D convolutions in a pyramidal architecture, the method gradually squeezes high-level semantic and low-level geometric cues of the hypercorrelation into precise segmentation masks in coarse-to-fine manner. The significant performance improvements on standard few-shot segmentation benchmarks of PASCAL-5i, COCO-20i, and FSS-1000 verify the efficacy of the proposed method.

The task of reflection symmetry detection remains challenging due to significant variations and ambiguities of symmetry patterns in the wild. Furthermore, since the local regions are required to match in reflection for detecting a symmetry pattern, it is hard for standard convolutional networks, which are not equivariant to rotation and reflection, to learn the task. To address the issue, we introduce a new convolutional technique, dubbed the polar matching convolution, which leverages a polar feature pooling, a self-similarity encoding, and a systematic kernel design for axes of different angles. The proposed high-dimensional kernel convolution network effectively learns to discover symmetry patterns from real-world images, overcoming the limitations of standard convolution. In addition, we present a new dataset and introduce a self-supervised learning strategy by augmenting the dataset with synthesizing images. Experiments demonstrate that our method outperforms state-of-the-art methods in terms of accuracy and robustness.

The paradigm of differentiable programming has significantly enhanced the scope of machine learning via the judicious use of gradient-based optimization. However, standard differentiable programming methods (such as autodiff) typically require that the machine learning models be differentiable, limiting their applicability. Our goal in this paper is to use a new, principled approach to extend gradient-based optimization to functions well modeled by splines, which encompass a large family of piecewise polynomial models. We derive the form of the (weak) Jacobian of such functions and show that it exhibits a block-sparse structure that can be computed implicitly and efficiently. Overall, we show that leveraging this redesigned Jacobian in the form of a differentiable "layer'' in predictive models leads to improved performance in diverse applications such as image segmentation, 3D point cloud reconstruction, and finite element analysis. We also open-source the code at \url{https://github.com/idealab-isu/DSA}.

Discovering a solution in a combinatorial space is prevalent in many real-world problems but it is also challenging due to diverse complex constraints and the vast number of possible combinations. To address such a problem, we introduce a novel formulation, combinatorial construction, which requires a building agent to assemble unit primitives (i.e., LEGO bricks) sequentially -- every connection between two bricks must follow a fixed rule, while no bricks mutually overlap. To construct a target object, we provide incomplete knowledge about the desired target (i.e., 2D images) instead of exact and explicit volumetric information to the agent. This problem requires a comprehensive understanding of partial information and long-term planning to append a brick sequentially, which leads us to employ reinforcement learning. The approach has to consider a variable-sized action space where a large number of invalid actions, which would cause overlap between bricks, exist. To resolve these issues, our model, dubbed Brick-by-Brick, adopts an action validity prediction network that efficiently filters invalid actions for an actor-critic network. We demonstrate that the proposed method successfully learns to construct an unseen object conditioned on a single image or multiple views of a target object.

Conditional Generative Adversarial Networks (cGAN) generate realistic images by incorporating class information into GAN. While one of the most popular cGANs is an auxiliary classifier GAN with softmax cross-entropy loss (ACGAN), it is widely known that training ACGAN is challenging as the number of classes in the dataset increases. ACGAN also tends to generate easily classifiable samples with a lack of diversity. In this paper, we introduce two cures for ACGAN. First, we identify that gradient exploding in the classifier can cause an undesirable collapse in early training, and projecting input vectors onto a unit hypersphere can resolve the problem. Second, we propose the Data-to-Data Cross-Entropy loss (D2D-CE) to exploit relational information in the class-labeled dataset. On this foundation, we propose the Rebooted Auxiliary Classifier Generative Adversarial Network (ReACGAN). The experimental results show that ReACGAN achieves state-of-the-art generation results on CIFAR10, Tiny-ImageNet, CUB200, and ImageNet datasets. We also verify that ReACGAN benefits from differentiable augmentations and that D2D-CE harmonizes with StyleGAN2 architecture. Model weights and a software package that provides implementations of representative cGANs and all experiments in our paper are available at https://github.com/POSTECH-CVLab/PyTorch-StudioGAN.

Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning. Recent emergence of Transformer networks, which replace convolution layers with self-attention blocks, has revealed the limitation of stationary convolution kernels and opened the door to the era of dynamic feature transforms. The existing dynamic transforms, including self-attention, however, are all limited for video understanding where correspondence relations in space and time, i.e., motion information, are crucial for effective representation. In this work, we introduce a relational feature transform, dubbed the relational self-attention (RSA), that leverages rich structures of spatio-temporal relations in videos by dynamically generating relational kernels and aggregating relational contexts. Our experiments and ablation studies show that the RSA network substantially outperforms convolution and self-attention counterparts, achieving the state of the art on the standard motion-centric benchmarks for video action recognition, such as Something-Something-V1&V2, Diving48, and FineGym.

Extracting local descriptors or features is an essential step in solving image matching problems. Recent methods in the literature mainly focus on extracting effective descriptors, without much attention to the size of the descriptors. In this work, we study how to learn a compact yet effective local descriptor. The proposed method distills multiple intermediate features of a pretrained convolutional neural network to encode different levels of visual information from local textures to non-local semantics, resulting in local descriptors with a designated dimension. Experiments on standard benchmarks for semantic correspondence show that it achieves significantly improved performance over existing models, with up to a 100 times smaller size of descriptors. Furthermore, while trained on a small-sized dataset for semantic correspondence, the proposed method also generalizes well to other image matching tasks, performing comparable result to the state of the art on wide-baseline matching and visual localization benchmarks.

Generative Adversarial Networks (GANs), while widely successful in modeling complex data distributions, have not yet been sufficiently leveraged in scientific computing and design. Reasons for this include the lack of flexibility of GANs to represent discrete-valued image data, as well as the lack of control over physical properties of generated samples. We propose a new conditional generative modeling approach (InvNet) that efficiently enables modeling discrete-valued images, while allowing control over their parameterized geometric and statistical properties. We evaluate our approach on several synthetic and real world problems: navigating manifolds of geometric shapes with desired sizes; generation of binary two-phase materials; and the (challenging) problem of generating multi-orientation polycrystalline microstructures.

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few gradient-descent iterations during tracking while pruning its network channels using the target ground-truth at the first frame. Such a learning problem is formulated as a meta-learning task, where a meta-tracker is trained by updating its meta-parameters for initial weights, learning rates, and pruning masks through carefully designed tracking simulations. The integrated meta-tracker greatly improves tracking performance by accelerating the convergence of online learning and reducing the cost of feature computation. Experimental evaluation on the standard datasets demonstrates its outstanding accuracy and speed compared to the state-of-the-art methods.

Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity. In contrast, the latter class enables fast and reliable convergence, but cannot consider the rich data-to-data relations. This paper presents a new proxy-based loss that takes advantages of both pair- and proxy-based methods and overcomes their limitations. Thanks to the use of proxies, our loss boosts the speed of convergence and is robust against noisy labels and outliers. At the same time, it allows embedding vectors of data to interact with each other in its gradients to exploit data-to-data relations. Our method is evaluated on four public benchmarks, where a standard network trained with our loss achieves state-of-the-art performance and most quickly converges.

This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to extract a collection of mid-level features for semantic phrases in a text query, which corresponds to important semantic entities described in the query (e.g., actors, objects, and actions), and reflect bi-modal interactions between the linguistic features of the query and the visual features of the video in multiple levels. The proposed method effectively predicts the target time interval by exploiting contextual information from local to global during bi-modal interactions. Through in-depth ablation studies, we find out that incorporating both local and global context in video and text interactions is crucial to the accurate grounding. Our experiment shows that the proposed method outperforms the state of the arts on Charades-STA and ActivityNet Captions datasets by large margins, 7.44% and 4.61% points at Recall@tIoU=0.5 metric, respectively.

We present a novel discriminator for GANs that improves realness and diversity of generated samples by learning a structured hypersphere embedding space using spherical circles. The proposed discriminator learns to populate realistic samples around the longest spherical circle, i.e., a great circle, while pushing unrealistic samples toward the poles perpendicular to the great circle. Since longer circles occupy larger area on the hypersphere, they encourage more diversity in representation learning, and vice versa. Discriminating samples based on their corresponding spherical circles can thus naturally induce diversity to generated samples. We also extend the proposed method for conditional settings with class labels by creating a hypersphere for each category and performing class-wise discrimination and update. In experiments, we validate the effectiveness for both unconditional and conditional generation on standard benchmarks, achieving the state of the art.

We introduce a novel stochastic regularization technique for deep neural networks, which decomposes a layer into multiple branches with different parameters and merges stochastically sampled combinations of the outputs from the branches during training. Since the factorized branches can collapse into a single branch through a linear operation, inference requires no additional complexity compared to the ordinary layers. The proposed regularization method, referred to as StochasticBranch, is applicable to any linear layers such as fully-connected or convolution layers. The proposed regularizer allows the model to explore diverse regions of the model parameter space via multiple combinations of branches to find better local minima. An extensive set of experiments shows that our method effectively regularizes networks and further improves the generalization performance when used together with other existing regularization techniques.

Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not. Such a binary indicator covers only a limited subset of image relations, and is not sufficient to represent semantic similarity between images described by continuous and/or structured labels such as object poses, image captions, and scene graphs. Motivated by this, we present a novel method for deep metric learning using continuous labels. First, we propose a new triplet loss that allows distance ratios in the label space to be preserved in the learned metric space. The proposed loss thus enables our model to learn the degree of similarity rather than just the order. Furthermore, we design a triplet mining strategy adapted to metric learning with continuous labels. We address three different image retrieval tasks with continuous labels in terms of human poses, room layouts and image captions, and demonstrate the superior performance of our approach compared to previous methods.

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conducted on different tasks show that the proposed method improves educated student models with a significant margin. In particular for metric learning, it allows students to outperform their teachers' performance, achieving the state of the arts on standard benchmark datasets.

Learning with complete or partial supervision is power- ful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an important field of research. In computer vision, unsu- pervised learning comes in various guises. We focus here on the unsupervised discovery and matching of object cate- gories among images in a collection, following the work of Cho et al. [12]. We show that the original approach can be reformulated and solved as a proper optimization problem. Experiments on several benchmarks establish the merit of our approach.

We propose a new algorithm for hyperparameter selection in machine learning algorithms. The algorithm is a novel modification of Harmonica, a spectral hyperparameter selection approach using sparse recovery methods. In particular, we show that a special encoding of hyperparameter space enables a natural group-sparse recovery formulation, which when coupled with HyperBand (a multi-armed bandit strategy) leads to improvement over existing hyperparameter optimization methods such as Successive Halving and Random Search. Experimental results on image datasets such as CIFAR-10 confirm the benefits of our approach.

Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by “hyperpixels” that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.

Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks. We introduce a simple yet effective approach to improving cGANs by measuring the discrepancy between the data distribution and the model distribution on given samples. The proposed measure, coined the gap of log-densities (GOLD), provides an effective self-diagnosis for cGANs while being efficiently, computed from the discriminator. We propose three applications of the GOLD: example re-weighting, rejection sampling, and active learning, which improve the training, inference, and data selection of cGANs, respectively. Our experimental results demonstrate that the proposed methods outperform corresponding baselines for all three applications on different image datasets.

Filtering images using a guidance signal, a process called guided or joint image filtering, has been used in various tasks in computer vision and computational photography, particularly for noise reduction and joint upsampling. This uses an additional guidance signal as a structure prior, and transfers the structure of the guidance signal to an input image, restoring noisy or altered image structure. The main drawbacks of such a data-dependent framework are that it does not consider structural differences between guidance and input images, and that it is not robust to outliers. We propose a novel SD (for static/dynamic) filter to address these problems in a unified framework, and jointly leverage structural information from guidance and input images. Guided image filtering is formulated as a nonconvex optimization problem, which is solved by the majorize-minimization algorithm. The proposed algorithm converges quickly while guaranteeing a local minimum. The SD filter effectively controls the underlying image structure at different scales, and can handle a variety of types of data from different sensors. It is robust to outliers and other artifacts such as gradient reversal and global intensity shift, and has good edge-preserving smoothing properties. We demonstrate the flexibility and effectiveness of the proposed SD filter in a variety of applications, including depth upsampling, scale-space filtering, texture removal, flash/non-flash denoising, and RGB/NIR denoising.

Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that the corresponding sparse proposal flow can effectively be transformed into a conventional dense flow field. We introduce two new challenging datasets that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use these benchmarks to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.

Visual attention plays an important role to understand images and demonstrates its effectiveness in generating natural language descriptions of images. On the other hand, recent studies show that language associated with an image can steer visual attention in the scene during our cognitive process. Inspired by this, we introduce a text-guided attention model for image captioning, which learns to drive visual attention using associated captions. For this model, we propose an exemplar-based learning approach that retrieves from training data associated captions with each image, and use them to learn attention on visual features. Our attention model enables to describe a detailed state of scenes by distinguishing small or confusable objects effectively. We validate our model on MS-COCO Captioning benchmark and achieve the state-of-the-art performance in standard metrics.

We propose Quadruplet Convolutional Neural Networks (Quad-CNN) for multi-object tracking, which learn to associate object detections across frames using quadruplet losses. The proposed networks consider target appearances together with their temporal adjacencies for data association. Unlike conventional ranking losses, the quadruplet loss enforces an additional constraint that makes temporally adjacent detections more closely located than the ones with large temporal gaps. We also employ a multi-task loss to jointly learn object association and bounding box regression for better localization. The whole network is trained end-to-end. For tracking, the target association is performed by minimax label propagation using the metric learned from the proposed network. We evaluate performance of our multi-object tracking algorithm on public MOT Challenge datasets, and achieve outstanding results.

This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with hand-crafted features, or learning a correspondence model for appearance only. We propose instead a convolutional neural network architecture, called SCNet, for learning a geometrically plausible model for semantic correspondence. SCNet uses region proposals as matching primitives, and explicitly incorporates geometric consistency in its loss function. It is trained on image pairs obtained from the PASCAL VOC 2007 keypoint dataset, and a comparative evaluation on several standard benchmarks demonstrates that the proposed approach substantially outperforms both recent deep learning architectures and previous methods based on hand-crafted features.

Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that proposal flow can effectively be transformed into a conventional dense flow field. We introduce a new dataset that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use this benchmark to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.

We address the problem of learning a pose-aware, compact embedding that projects images with similar human poses to be placed close-by in the embedding space. The embedding function is built on a deep convolutional network, and trained with triplet-based rank constraints on real image data. This architecture allows us to learn a robust representation that captures differences in human poses by effectively factoring out variations in clothing, background, and imaging conditions in the wild. For a variety of pose-related tasks, the proposed pose embedding provides a cost-efficient and natural alternative to explicit pose estimation, circumventing challenges of localizing body joints. We demonstrate the efficacy of the embedding on pose-based image retrieval and action recognition problems.

This paper addresses the problem of matching common node correspondences among multiple graphs referring to an identical or related structure. This multi-graph matching problem involves two correlated components: i) the local pairwise matching affinity across pairs of graphs; ii) the global matching consistency that measures the uniqueness of the pairwise matchings by different composition orders. Previous studies typically either enforce the matching consistency constraints in the beginning of an iterative optimization, which may propagate matching error both over iterations and across graph pairs; or separate affinity optimization and consistency enforcement into two steps. This paper is motivated by the observation that matching consistency can serve as a regularizer in the affinity objective function especially when the function is biased due to noises or inappropriate modeling. We propose composition-based multi-graph matching methods to incorporate the two aspects by optimizing the affinity score, meanwhile gradually infusing the consistency. We also propose two mechanisms to elicit the common inliers against outliers. Compelling results on synthetic and real images show the competency of our algorithms.

This paper addresses unsupervised discovery and localization of dominant objects from a noisy image collection with multiple object classes. The setting of this problem is fully unsupervised, without even image-level annotations or any assumption of a single dominant class. This is far more general than typical colocalization, cosegmentation, or weakly-supervised localization tasks. We tackle the discovery and localization problem using a part-based region matching approach: We use off-the-shelf region proposals to form a set of candidate bounding boxes for objects and object parts. These regions are efficiently matched across images using a probabilistic Hough transform that evaluates the confidence for each candidate correspondence considering both appearance and spatial consistency. Dominant objects are discovered and localized by comparing the scores of candidate regions and selecting those that stand out over other regions containing them. Extensive experimental evaluations on standard benchmarks demonstrate that the proposed approach significantly outperforms the current state of the art in colocalization, and achieves robust object discovery in challenging mixed-class datasets.

Regularizing images under a guidance signal has been used in various tasks in computer vision and computational photography, particularly for noise reduction and joint upsampling. The aim is to transfer fine structures of guidance signals to input images, restoring noisy or altered structures. One of main drawbacks in such a data-dependent framework is that it does not handle differences in structure between guidance and input images. We address this problem by jointly leveraging structural information of guidance and input images. Image filtering is formulated as a nonconvex optimization problem, which is solved by the majorization-minimization algorithm. The proposed algorithm converges quickly while guaranteeing a local minimum. It effectively controls image structures at different scales and can handle a variety of types of data from different sensors. We demonstrate the flexibility and effectiveness of our model in several applications including depth super-resolution, scale-space filtering, texture removal, flash/non-flash denoising, and RGB/NIR denoising.

This paper addresses the problem of automatically localizing dominant objects as spatio-temporal tubes in a noisy collection of videos with minimal or even no supervision. We formulate the problem as a combination of two complementary processes: discovery and tracking. The first one establishes correspondences between prominent regions across videos, and the second one associates similar object regions within the same video. Interestingly, our algorithm also discovers the implicit topology of frames associated with instances of the same object class across different videos, a role normally left to supervisory information in the form of class labels in conventional image and video understanding methods. Indeed, as demonstrated by our experiments, our method can handle video collections featuring multiple object classes, and substantially outperforms the state of the art in colocalization, even though it tackles a broader problem with much less supervision.

Interests in manufacturing process management and analysis are increasing, but it is difficult to conduct process analysis due to the increase of manufacturing data. Therefore, we suggest a manufacturing data analysis system that collects event logs from so-called big data and analyzes the collected logs with process mining. There are two kinds of big data generated from manufacturing processes, structured data and unstructured data. Usually, manufacturing process analysis is conducted by using only structured data, however the proposed system uses both structured and unstructured data for enhancing the process analysis results. The system automatically discovers a process model and conducts various performance analysis on the manufacturing processes.

A major challenge in real-world feature matching problems is to tolerate the numerous outliers arising in typical visual tasks. Variations in object appearance, shape, and structure within the same object class make it harder to distinguish inliers from outliers due to clutters. In this paper, we propose a max-pooling approach to graph matching, which is not only resilient to deformations but also remarkably tolerant to outliers. The proposed algorithm evaluates each candidate match using its most promising neighbors, and gradually propagates the corresponding scores to update the neighbors. As final output, it assigns a reliable score to each match together with its supporting neighbors, thus providing contextual information for further verification. We demonstrate the robustness and utility of our method with synthetic and real image experiments.

Many tasks in computer vision are formulated as graph matching problems. Despite the NP-hard nature of the problem, fast and accurate approximations have led to significant progress in a wide range of applications. Learning graph models from observed data, however, still remains a challenging issue. This paper presents an effective scheme to parameterize a graph model, and learn its structural attributes for visual object matching. For this, we propose a graph representation with histogram-based attributes, and optimize them to increase the matching accuracy. Experimental evaluations on synthetic and real image datasets demonstrate the effectiveness of our approach, and show significant improvement in matching accuracy over graphs with pre-defined structures.

Graph matching is widely used in a variety of scientific fields, including computer vision, due to its powerful performance, robustness, and generality. Its computational complexity, however, limits the permissible size of input graphs in practice. Therefore, in real-world applications, the initial construction of graphs to match becomes a critical factor for the matching performance, and often leads to unsatisfactory results. In this paper, to resolve the issue, we propose a novel progressive framework which combines probabilistic progression of graphs with matching of graphs. The algorithm efficiently re-estimates in a Bayesian manner the most plausible target graphs based on the current matching result, and guarantees to boost the matching objective at the subsequent graph matching. Experimental evaluation demonstrates that our approach effectively handles the limits of conventional graph matching and achieves significant improvement in challenging image matching problems.

Mode-seeking has been widely used as a powerful data analysis technique for clustering and filtering in a metric feature space. We introduce a versatile and efficient mode-seeking method for “graph” representation where general embedding of relational data is possible beyond metric spaces. Exploiting the global structure of the graph by random walks, our method intrinsically combines mode-seeking with ranking on the graph, and performs robust analysis by seeking high-ranked authoritative data and suppressing low-ranked noise and outliers. This enables mode-seeking to be applied to a large class of challenging real-world problems involving graph representation which frequently arises in computer vision. We demonstrate our method on various synthetic experiments and real applications dealing with noisy and complex data such as scene summarization and object-based image matching.

Establishing correspondences between two feature sets is a fundamental issue in computer vision, pattern recognition, and machine learning. This problem can be well formulated as graph matching in which nodes represent feature points while edges describe pairwise relations between feature points. Recently, several researches have tried to embed higher-order relations of feature points by hyper-graph matching formulations. In this paper, we generalize the previous hyper-graph matching formulations to cover relations of features in arbitrary orders, and propose a novel state-of-the-art algorithm by reinterpreting the random walk concept on the hyper-graph in a probabilistic manner. Adopting personalized jumps with a reweighting scheme, the algorithm effectively reflects the one-to-one matching constraints during the random walk process. Comparative experiments on synthetic data and real images show that the proposed method clearly outperforms existing algorithms especially in the presence of noise and outliers.

In this paper, a novel hierarchical clustering method using link analysis techniques is introduced. The algorithm is formulated as an authority seeking procedure on graphs, which computes the shifts toward nodes with high authority scores. For the authority shift, we adopted the personalized PageRank score of the graph. Based on the concept of authority seeking, we achieve hierarchical clustering by iteratively propagating the authority scores to other nodes and shifting authority nodes. This scheme solves the chicken-egg difficulty in hierarchical clustering by a semiglobal bottom-up approach exploiting the global structure of the graph. The experimental evaluation demonstrates that our algorithm is more powerful compared with existing graph-based approaches in clustering and image segmentation tasks.

We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or modeltest settings between images. Our method can detect and segment identical objects directly from a single image or a handful of images without any supervision. To detect and segment all the object-level correspondences from the given images, a novel multi-layer match-growing method is proposed that starts from initial local feature matches and explores the images by intra-layer expansion and inter-layer merge. It estimates geometric relations between object entities and establishes ‘object correspondence networks’ that connect matching objects. Experiments demonstrate robust performance of our method on challenging datasets.

We propose a novel stochastic graph matching algorithm based on data-driven Markov Chain Monte Carlo (DDMCMC) sampling technique. The algorithm explores the solution space efficiently and avoid local minima by taking advantage of spectral properties of the given graphs in data-driven proposals. Thus, it enables the graph matching to be robust to deformation and outliers arising from the practical correspondence problems. Our comparative experiments using synthetic and real data demonstrate that the algorithm outperforms the state-of-the-art graph matching algorithms.

In this paper, we present a method that recognizes single or multiple common actions between a pair of video sequences. We establish an energy function that evaluates geometric and photometric consistency, and solve the action recognition problem by optimizing the energy function. The proposed stochastic inference algorithm based on the Monte Carlo method explores the video pair from the local spatio-temporal interest point matches to find the common actions. Our algorithm works in unsupervised way without prior knowledge about the type and the number of common actions. Experiments show that our algorithm produces promising results on single and multiple action recognition.

We present a novel and robust method for localizing and segmenting bilaterally symmetric patterns from real-world images. On the basis of symmetrically matched pairs of local features, our method expands and merges condent local symmetric region matches by exploiting both photometric similarity and geometric consistency via our new symmetry-growing framework. It overcomes the limitations of the previous local-feature based approaches by efciently exploring the image space to grow symmetry beyond the detected symmetric features. The experimental evaluation demonstrates that our method successfully detects and segments multiple symmetric patterns from real-world images, and clearly outperforms the state-of-the-art methods in accuracy and robustness.

We present an efficient method for feature correspondence and object-based image matching, which exploits both photometric similarity and pairwise geometric consistency from local invariant features. We formulate object-based image matching as an unsupervised multi-class clustering problem on a set of candidate feature matches, and propose a novel pairwise dissimilarity measure and a robust linkage model in the framework of hierarchical agglomerative clustering. The algorithm handles significant amount of outliers and deformation as well as multiple clusters, thus enabling simultaneous feature matching and clustering from real-world image pairs with significant clutter and multiple deformable objects. The experimental evaluation on feature correspondence, object recognition, and object-based image matching demonstrates that our method is robust to both outliers and deformation, and applicable to a wide range of image matching problems.

We present a novel object-specific segmentation method which can be used in view-based object recognition systems. Previous object segmentation approaches generate inexact results especially in partially occluded and cluttered environment because their top-down strategies fail to explain the details of various specific objects. On the contrary, our segmentation method efficiently exploits the information of the matched model views in view-based recognition because the aligned model view to the input image can serve as the best top-down cue for object segmentation. In this paper, we cast the problem of partially occluded object segmentation as that of labelling displacement and foreground status simultaneously for each pixel between the aligned model view and an input image. The problem is formulated by a maximum a posteriori Markov random field (MAP-MRF) model which minimizes a particular energy function. Our method overcomes complex occlusion and clutter and provides accurate segmentation boundaries by combining a bottom-up segmentation cue together. We demonstrate the efficiency and robustness of it by experimental results on various objects under occluded and cluttered environments.