The resolution of voxel queries significantly influences the quality of view transformation in camera-based 3D occupancy prediction. However, computational constraints and the practical necessity for real-time deployment require smaller query resolutions, which inevitably leads to an information loss. Therefore, it is essential to encode and preserve rich visual details within limited query sizes while ensuring a comprehensive representation of 3D occupancy. To this end, we introduce ProtoOcc, a novel occupancy network that leverages prototypes of clustered image segments in view transformation to enhance low-resolution context. In particular, the mapping of 2D prototypes onto 3D voxel queries encodes high-level visual geometries and complements the loss of spatial information from reduced query resolutions. Additionally, we design a multi-perspective decoding strategy to efficiently disentangle the densely compressed visual cues into a high-dimensional 3D occupancy scene. Experimental results on both Occ3D and SemanticKITTI benchmarks demonstrate the effectiveness of the proposed method, showing clear improvements over the baselines. More importantly, ProtoOcc achieves competitive performance against the baselines even with 75% reduced voxel resolution. Project page: https://kuai-lab.github.io/cvpr2025protoocc.

Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution. To reduce such domain gaps and thus to make 3DOD models more generalizable, we introduce a novel unsupervised domain adaptation (UDA) method, called CMDA, which (i) leverages visual semantic cues from an image modality (i.e., camera images) as an effective semantic bridge to close the domain gap in the cross-modal Bird's Eye View (BEV) representations. Further, (ii) we also introduce a self-training-based learning strategy, wherein a model is adversarially trained to generate domain-invariant features, which disrupt the discrimination of whether a feature instance comes from a source or an unseen target domain. Overall, our CMDA framework guides the 3DOD model to generate highly informative and domain-adaptive features for novel data distributions. In our extensive experiments with large-scale benchmarks, such as nuScenes, Waymo, and KITTI, those mentioned above provide significant performance gains for UDA tasks, achieving state-of-the-art performance.

Social relations have substantial impacts on the potential trajectories of each individual. Modeling these dynamics has been a central solution for more precise and accurate trajectory forecasting. However, previous works ignore the importance of ‘social depth’, meaning the influences flowing from different degrees of social relations. In this work, we propose HighGraph, a graph-based pedestrian relational reasoning method that captures the higherorder dynamics of social interactions. First, we construct a collision-aware relation graph based on the agents' observed trajectories. Upon this graph structure, we build our core module that aggregates the agent features from diverse social distances. As a result, the network is able to model complex social relations, thereby yielding more accurate and socially acceptable trajectories. Our High-Graph is a plug-and-play module that can be easily applied to any current trajectory predictors. Extensive experiments with ETH/UCY and SDD datasets demonstrate that our HighGraph noticeably improves the previous state-of-the-art baselines both quantitatively and qualitatively.

In autonomous driving and robotics, there is a growing interest in utilizing short-term historical data to enhance multi-camera 3D object detection, leveraging the continuous and correlated nature of input video streams. Recent work has focused on spatially aligning BEV-based features over timesteps. However, this is often limited as its gain does not scale well with long-term past observations. To address this, we advocate for supervising a model to predict objects’ poses given past observations, thus explicitly guiding to learn objects’ temporal cues. To this end, we propose a model called DAP (Detection After Prediction), consisting of a two-branch network: (i) a branch responsible for forecasting the current objects’ poses given past observations and (ii) another branch that detects objects based on the current and past observations. The features predicting the current objects from branch (i) is fused into branch (ii) to transfer predictive knowledge. We conduct extensive experiments with the large-scale nuScenes datasets, and we observe that utilizing such predictive information significantly improves the overall detection performance. Our model can be used plug-and-play, showing consistent performance gain.

Recent advances in 3D object detection leveraging multi-view cameras have demonstrated their practical and economical value in various challenging vision tasks. However, typical supervised learning approaches face challenges in achieving satisfactory adaptation toward unseen and unlabeled target datasets (i.e., direct transfer) due to the inevitable geometric misalignment between the source and target domains. In practice, we also encounter constraints on resources for training models and collecting annotations for the successful deployment of 3D object detectors. In this paper, we propose Unified Domain Generalization and Adaptation (UDGA), a practical solution to mitigate those drawbacks. We first propose Multi-view Overlap Depth Constraint that leverages the strong association between multi-view, significantly alleviating geometric gaps due to perspective view changes. Then, we present a Label-Efficient Domain Adaptation approach to handle unfamiliar targets with significantly fewer amounts of labels (i.e., 1$\%$ and 5$\%)$, while preserving well-defined source knowledge for training efficiency. Overall, UDGA framework enables stable detection performance in both source and target domains, effectively bridging inevitable domain gaps, while demanding fewer annotations. We demonstrate the robustness of UDGA with large-scale benchmarks: nuScenes, Lyft, and Waymo, where our framework outperforms the current state-of-the-art methods.

In autonomous driving applications, there is a strong preference for modeling the world in Bird’s-Eye View (BEV), as it leads to improved accuracy and performance. BEV features are widely used in perception tasks since they allow fusing information from multiple views in an efficient manner. However, BEV features generated from camera images are prone to be imprecise due to the difficulty of estimating depth in the perspective view. Improper placement of BEV features limits the accuracy of downstream tasks. We introduce a method for incorporating map information to improve perspective depth estimation from 2D camera images and thereby producing geometrically- and semantically-robust BEV features. We show that augmenting the camera images with the BEV map and map-to-camera projections can compensate for the depth uncertainty and enrich camera-only BEV features with road contexts. Experiments on the nuScenes dataset demonstrate that our method outperforms previous approaches using only camera images in segmentation and detection tasks.

Current text-to-image generation methods produce high-resolution and high-quality images, but they should not produce immoral images that may contain inappropriate content from the perspective of commonsense morality. Conventional approaches, however, often neglect these ethical concerns, and existing solutions are often limited to ensure moral compatibility. To address this, we propose a novel method that has three main capabilities: (1) our model recognizes the degree of visual commonsense immorality of a given generated image, (2) our model localizes immoral visual (and textual) attributes that make the image visually immoral, and (3) our model manipulates such immoral visual cues into a morally-qualifying alternative. We conduct experiments with various text-to-image generation models, including the state-of-the-art Stable Diffusion model, demonstrating the efficacy of our ethical image manipulation approach. Our human study further confirms that ours is indeed able to generate morally-satisfying images from immoral ones.

We present a novel framework for audio-guided localized image stylization. Sound often provides information about the specific context of a scene and is closely related to a certain part of the scene or object. However, existing image stylization works have focused on stylizing the entire image using an image or text input. Stylizing a particular part of the image based on audio input is natural but challenging. This work proposes a framework in which a user provides an audio input to localize the target in the input image and another to locally stylize the target object or scene. We first produce a fine localization map using an audio-visual localization network leveraging CLIP embedding space. We then utilize an implicit neural representation (INR) along with the predicted localization map to stylize the target based on sound information. The INR manipulates local pixel values to be semantically consistent with the provided audio input. Our experiments show that the proposed framework outperforms other audio-guided stylization methods. Moreover, we observe that our method constructs concise localization maps and naturally manipulates the target object or scene in accordance with the given audio input.

In recent years, video generation has become a prominent generative tool and has drawn significant attention. However, there is little consideration in audio-to-video generation, though audio contains unique qualities like temporal semantics and magnitude. Hence, we propose The Power of Sound (TPoS) model to incorporate audio input that includes both changeable temporal semantics and magnitude. To generate video frames, TPoS utilizes a latent stable diffusion model with textual semantic information, which is then guided by the sequential audio embedding from our pretrained Audio Encoder. As a result, this method produces audio reactive video contents. We demonstrate the effectiveness of TPoS across various tasks and compare its results with current state-of-the-art techniques in the field of audio-to-video generation. More examples are available at https://ku-vai.github.io/TPoS/

An autonomous driving system requires a 3D object detector, which must perceive all present road agents reliably to navigate an environment safely. However, real-world driving datasets often suffer from the problem of data imbalance, which causes difficulties in training a model that works well across all classes, resulting in an undesired imbalanced sub-optimal performance. In this work, we propose a method to address this data imbalance problem. Our method consists of two main components: (i) a LiDAR-based 3D object detector with per-class multiple detection heads where losses from each head are modified by dynamic weight average to be balanced. (ii) Contextual ground truth (GT) sampling, where we improve conventional GT sampling techniques by leveraging semantic information to augment point cloud with sampled ground truth GT objects. Our experiment with KITTI and nuScenes datasets confirms our proposed method’s effectiveness in dealing with the data imbalance problem, producing better detection accuracy compared to existing approaches.

A number of recent self-supervised learning methods have shown impressive performance on image classification and other tasks. A somewhat bewildering variety of techniques have been used, not always with a clear understanding of the reasons for their benefits, especially when used in combination. Here we treat the embeddings of images as point particles and consider model optimization as a dynamic process on this system of particles. Our dynamic model combines an attractive force for similar images, a locally dispersive force to avoid local collapse, and a global dispersive force to achieve a globally-homogeneous distribution of particles. The dynamic perspective highlights the advantage of using a delayed-parameter image embedding (a la BYOL) together with multiple views of the same image. It also uses a purely-dynamic local dispersive force (Brownian motion) that shows improved performance over other methods and does not require knowledge of other particle coordinates. The method is called MSBReg which stands for (i) a Multiview centroid loss, which applies an attractive force to pull different image view embeddings toward their centroid, (ii) a Singular value loss, which pushes the particle system toward spatially homogeneous density, (iii) a Brownian diffusive loss. We evaluate downstream classification performance of MSBReg on ImageNet as well as transfer learning tasks including fine-grained classification, multi-class object classification, object detection, and instance segmentation. In addition, we also show that applying our regularization term to other methods further improves their performance and stabilize the training by preventing a mode collapse.

The recent success of the generative model shows that leveraging the multi-modal embedding space can manipu-late an image using text information. However, manipulating an image with other sources rather than text, such as sound, is not easy due to the dynamic characteristics of the sources. Especially, sound can convey vivid emotions and dynamic expressions of the real world. Here, we propose a framework that directly encodes sound into the multi-modal (image-text) embedding space and manipulates an image from the space. Our audio encoder is trained to pro-duce a latent representation from an audio input, which is forced to be aligned with image and text representations in the multi-modal embedding space. We use a direct latent op-timization method based on aligned embeddings for sound-guided image manipulation. We also show that our method can mix different modalities, i.e., text and audio, which en-rich the variety of the image modification. The experiments on zero-shot audio classification and semantic-level image classification show that our proposed model outperforms other text and sound-guided state-of-the-art methods.

We introduce a motion forecasting (behavior prediction) method that meets the latency requirements for autonomous driving in dense urban environments without sacrificing accuracy. A whole-scene sparse input representation allows StopNet to scale to predicting trajectories for hundreds of road agents with reliable latency. In addition to predicting trajectories, our scene encoder lends itself to predicting whole-scene probabilistic occupancy grids, a complementary output representation suitable for busy urban environments. Occupancy grids allow the AV to reason collectively about the behavior of groups of agents without processing their individual trajectories. We demonstrate the effectiveness of our sparse input representation and our model in terms of computation and accuracy over three datasets. We further show that co-training consistent trajectory and occupancy predictions improves upon state-of-the-art performance under standard metrics.

In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, i.e. domain shift, may occur, which becomes a major factor impeding the generalization performance of the model. The research field to solve this problem is called domain generalization, and it alleviates the domain shift problem by extracting domain-invariant features explicitly or implicitly. In recent studies, contrastive learning-based domain generalization approaches have been proposed and achieved high performance. These approaches require sampling of the negative data pair. However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs. To address this issue, we propose a new regularization method for domain generalization based on contrastive learning, called self-supervised contrastive regularization (SelfReg). The proposed approach use only positive data pairs, thus it resolves various problems caused by negative pair sampling. Moreover, we propose a class-specific domain perturbation layer (CDPL), which makes it possible to effectively apply mixup augmentation even when only positive data pairs are used. The experimental results show that the techniques incorporated by SelfReg contributed to the performance in a compatible manner. In the recent benchmark, DomainBed, the proposed method shows comparable performance to the conventional state-of-the-art alternatives.

Humans learn to drive through both practice and theory, e.g. by studying the rules, while most self-driving systems are limited to the former. Being able to incorporate human knowledge of typical causal driving behaviour should benefit autonomous systems. We propose a new approach that learns vehicle control with the help of human advice. Specifically, our system learns to summarize its visual observations in natural language, predict an appropriate action response (e.g. "I see a pedestrian crossing, so I stop"), and predict the controls, accordingly. Moreover, to enhance interpretability of our system, we introduce a fine-grained attention mechanism which relies on semantic segmentation and object-centric RoI pooling. We show that our approach of training the autonomous system with human advice, grounded in a rich semantic representation, matches or outperforms prior work in terms of control prediction and explanation generation. Our approach also results in more interpretable visual explanations by visualizing object-centric attention maps. Code is available at https://github.com/JinkyuKimUCB/advisable-driving.

Inspired by human vision, we propose a new periphery-fovea multi-resolution driving model that predicts vehicle speed from dash camera videos. The peripheral vision module of the model processes the full video frames in low resolution with large receptive fields. Its foveal vision module selects sub-regions and uses high-resolution input from those regions to improve its driving performance. We train the fovea selection module with supervision from driver gaze. We show that adding high-resolution input from predicted human driver gaze locations significantly improves the driving accuracy of the model. Our periphery-fovea multi-resolution model outperforms a uni-resolution periphery-only model that has the same amount of floating-point operations. More importantly, we demonstrate that our driving model achieves a significantly higher performance gain in pedestrian-involved critical situations than in other non-critical situations. Our code is publicly available at https://github.com/pascalxia/periphery_fovea_driving.

Recent success suggests that deep neural control networks are likely to be a key component of self-driving vehicles. These networks are trained on large datasets to imitate human actions, but they lack semantic understanding of image contents. This makes them brittle and potentially unsafe in situations that do not match training data. Here, we propose to address this issue by augmenting training data with natural language advice from a human. Advice includes guidance about what to do and where to attend. We present the first step toward advice giving, where we train an end-to-end vehicle controller that accepts advice. The controller adapts the way it attends to the scene (visual attention) and the control (steering and speed). Attention mechanisms tie controller behavior to salient objects in the advice. We evaluate our model on a novel advisable driving dataset with manually annotated human-to-vehicle advice called Honda Research Institute-Advice Dataset (HAD). We show that taking advice improves the performance of the end-to-end network, while the network cues on a variety of visual features that are provided by advice. The dataset is available at https://usa.honda-ri.com/HAD.

Deep neural perception and control networks are likely to be a key component of self-driving vehicles. These models need to be explainable - they should provide easy-tointerpret rationales for their behavior - so that passengers, insurance companies, law enforcement, developers etc., can understand what triggered a particular behavior. Here we explore the use of visual explanations. These explanations take the form of real-time highlighted regions of an image that causally influence the network’s output (steering control). Our approach is two-stage. In the first stage, we use a visual attention model to train a convolution network endto- end from images to steering angle. The attention model highlights image regions that potentially influence the network’s output. Some of these are true influences, but some are spurious. We then apply a causal filtering step to determine which input regions actually influence the output. This produces more succinct visual explanations and more accurately exposes the network’s behavior. We demonstrate the effectiveness of our model on three datasets totaling 16 hours of driving. We first show that training with attention does not degrade the performance of the end-to-end network. Then we show that the network causally cues on a variety of features that are used by humans while driving.

As a great deal of data has been accumulated in various disciplines, the need for the integrative analysis of separate but relevant data sources is becoming more important. Combining data sources can provide global insight that is otherwise difficult to obtain from individual sources. Because of privacy, regulations, and other issues, many large-scale data repositories remain closed off from the outside, raising what has been termed the data silo issue. The huge volume of today's big data often leads to computational challenges, adding another layer of complexity to the solution. In this paper, we propose a novel method called collaborative analytics by ensemble learning (CABEL), which attempts to resolve the main hurdles regarding the silo issue: accuracy, privacy, and computational efficiency. CABEL represents the data stored in each silo as a compact aggregate of samples called the silo signature. The compact representation provides computational efficiency and privacy preservation but makes it challenging to produce accurate analytics. To resolve this challenge, we formulate the problem of attribute domain sampling and reconstruction, and propose a solution called the Chebyshev subset. To model collaborative efforts to analyze semantically linked but structurally disconnected databases, CABEL utilizes a new ensemble learning technique termed the weighted bagging of base classifiers. We demonstrate the effectiveness of CABEL by testing with a nationwide health-insurance data set containing approximately 4,182,000,000 records collected from the entire population of an Organisation for Economic Co-operation and Development (OECD) country in 2012. In our binary classification tests, CABEL achieved median recall, precision, and F-measure values of 89%, 64%, and 76%, respectively, although only 0.001–0.00001% of the original data was used for model construction, while maintaining data privacy and computational efficiency.

MOTIVATION: Capillary electrophoresis (CE) of nucleic acids is a workhorse technology underlying high-throughput genome analysis and large-scale chemical mapping for nucleic acid structural inference. Despite the wide availability of CE-based instruments, there remain challenges in leveraging their full power for quantitative analysis of RNA and DNA structure, thermodynamics and kinetics. In particular, the slow rate and poor automation of available analysis tools have bottlenecked a new generation of studies involving hundreds of CE profiles per experiment. RESULTS: We propose a computational method called high-throughput robust analysis for capillary electrophoresis (HiTRACE) to automate the key tasks in large-scale nucleic acid CE analysis, including the profile alignment that has heretofore been a rate-limiting step in the highest throughput experiments. We illustrate the application of HiTRACE on 13 datasets representing 4 different RNAs, 3 chemical modification strategies and up to 480 single mutant variants; the largest datasets each include 87 360 bands. By applying a series of robust dynamic programming algorithms, HiTRACE outperforms prior tools in terms of alignment and fitting quality, as assessed by measures including the correlation between quantified band intensities between replicate datasets. Furthermore, while the smallest of these datasets required 7-10 h of manual intervention using prior approaches, HiTRACE quantitation of even the largest datasets herein was achieved in 3-12 min. The HiTRACE method, therefore, resolves a critical barrier to the efficient and accurate analysis of nucleic acid structure in experiments involving tens of thousands of electrophoretic bands.

MOTIVATION: For high-throughput prediction of the helical arrangements of large RNA molecules, an innovative method termed multiplexed hydroxyl radical (*OH) cleavage analysis (MOHCA) has been proposed. A key step in this promising technique is to detect peaks accurately from noisy radioactivity profiles. Since manual peak finding is laborious and prone to error, an automated peak detection method to improve the accuracy and throughput of MOHCA is required. Existing methods were not applicable to MOHCA due to their high false positive rates. RESULTS: We developed a two-step computational method that can detect peaks from MOHCA profiles in a robust manner. The first step exploits an ensemble of linear and non-linear signal processing techniques to find true peak candidates. In the second step, a binary classifier trained with the characteristics of true and false peaks is used to eliminate false peaks out of the peak candidates. We tested the proposed approach with 2002 MOHCA cleavage profiles and obtained the median recall, precision and F-measure values of 0.917, 0.750 and 0.830, respectively. Compared with the alternatives considered, the proposed method was able to handle false peaks substantially better, thus resulting in 51.0-71.8% higher median values of precision and F-measure. AVAILABILITY: The software and supplementary data are available at http://dna.korea.ac.kr/pub/mohca.