Mingze Xu, Zijing Zhao, Qiming Peng, Houwen Peng, Han Hu, Zhanhui Kang, Yuxing Han. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmarks often fail to rigorously evaluate the nuanced reasoning capabilities required for complex, real-world problemsolving, particularly in multi-disciplinary and multimodal contexts. In this paper, we introduce a graduate-level, multi-disciplinary, EnglishChinese benchmark, dubbed as Reasoning Bench (RBench), for assessing the reasoning capability of both language and multimodal models. RBench spans 1,094 questions across 108 subjects for language model evaluation and 665 questions across 83 subjects for multimodal model testing. These questions are meticulously curated to ensure rigorous difficulty calibration, subject balance, and cross-linguistic alignment, enabling the assessment to be an Olympiad-level multidisciplinary benchmark. We evaluate many models such as o1, GPT-4o, DeepSeek-R1, etc. Experimental results indicate that advanced models perform poorly on complex reasoning, especially multimodal reasoning. Even the top-performing model OpenAI o1 achieves only 53.2% accuracy on our multimodal evaluation. Data and code are made publicly available athttps://evalmodels.github.io/rbench/

The rapid advancement of native multi-modal models and omni-models, exemplified by GPT-4o, Gemini and o3 with their capability to process and generate content across modalities such as text and images, marks a significant milestone in the evolution of intelligence. Systematic evaluation of their multi-modal output capabilities in visual thinking process (a.k.a., multi-modal chain of thought, M-CoT) becomes critically important. However, existing benchmarks for evaluating multi-modal models primarily focus on assessing multi-modal inputs and text-only reasoning process while neglecting the importance of reasoning through multi-modal outputs. In this paper, we present a benchmark, dubbed as RBench-V, designed to assess models’ vision-indispensable reasoning. To conduct RBench-V, we carefully hand-pick 803 questions covering math, physics, counting and games. Unlike problems in previous benchmarks, which typically specify certain input modalities, RBench-V presents problems centered on multi-modal outputs, which require image manipulation, such as generating novel images and constructing auxiliary lines to support reasoning process. We evaluate numerous open- and closed-source models on RBench-V, including o3, Gemini 2.5 pro, Qwen2.5-VL, etc. Even the best-performing model, o3, achieves only 25.8% accuracy on RBench-V, far below the human score of 82.3%, which shows current models struggle to leverage multi-modal reasoning. Data and code are available at https://evalmodels.github.io/rbenchv.

Vision transformer (ViT) variants have made rapid advances on a variety of computer vision tasks. However, their performance on corrupted inputs, which are inevitable in realistic use cases due to variations in lighting and weather, has not been explored comprehensively. In this paper, we probe the robustness gap among ViT variants and ask how these modern architectural developments affect performance under common types of corruption. Through extensive and rigorous benchmarking, we demonstrate that simple architectural designs such as overlapping patch embedding and convolutional feed-forward networks can promote the robustness of ViTs. Moreover, since the de facto training of ViTs relies heavily on data augmentation, exactly which augmentation strategies make ViTs more robust is worth investigating. We survey the efficacy of previous methods and verify that adversarial noise training is powerful. In addition, we introduce a novel conditional method for generating dynamic augmentation parameters conditioned on input images, which offers state-of-the-art robustness to common corruptions.

Differentiable architecture search (DARTS) has attracted much attention due to its simplicity and significant improvement in efficiency. However, the excessive accumulation of the skip connection, when training epochs become large, makes it suffer from weak stability and low robustness, thus limiting its practical applications. Many works have attempted to restrict the accumulation of skip connections by indicators or manual design. These methods, however, are susceptible to human priors and hyperparameters. In this work, we suggest a more subtle and direct approach that no longer explicitly searches for skip connections in the search stage, based on the paradox that skip connections were proposed to guarantee the performance of very deep networks, but the networks in the search stage of DARTS are actually very shallow. Instead, by introducing channel importance ranking and channel allocation strategy, the skip connections are implicitly searched and automatically refilled unimportant channels in the evaluation stage. Our method, dubbed adaptive channel allocation (ACA) strategy, is a general-purpose approach for DARTS, which universally works in DARTS variants without introducing human priors, indicators, or hyperparameters. Extensive experiments on various datasets and DARTS variants verify that the ACA strategy is the most effective one among the existing methods in improving robustness and dealing with the collapse issue when training epochs become large.

We present InstructDiffusion, a unified and generic framework for aligning computer vision tasks with hu-man instructions. Unlike existing approaches that integrate prior knowledge and pre-define the output space (e.g., categories and coordinates) for each vision task, we cast diverse vision tasks into a human-intuitive image-manipulating pro-cess whose output space is a flexible and interactive pixel space. Concretely, the model is built upon the diffusion process and is trained to predict pixels according to user instructions, such as encircling the man's left shoulder in red or applying a blue mask to the left car. InstructDiffusion could handle a variety of vision tasks, including understanding tasks (such as segmentation and keypoint de-tection) and generative tasks (such as editing and enhance-ment) and outperforms prior methods on novel datasets. This represents a solid step towards a generalist modeling interface for vision tasks, advancing artificial general intelligence in the field of computer vision.

We propose a method to efficiently equip the Segment Anything Model (SAM) with the ability to generate regional captions. SAM presents strong generalizability to segment anything while is short for semantic understanding. By introducing a lightweight query-based feature mixer, we align the region-specific features with the embedding space of language models for later caption generation. As the number of trainable parameters is small (typically in the order of tens of millions), it costs less computation, less memory usage, and less communication bandwidth, resulting in both fast and scalable training. To address the scarcity problem of regional caption data, we propose to first pretrain our model on objection detection and segmentation tasks. We call this step weak supervision pretraining since the pretraining data only contains category names instead of full-sentence descriptions. The weak supervision pretraining al-lows us to leverage many publicly available object detection and segmentation datasets. We conduct extensive experiments to demonstrate the superiority of our method and validate each design choice. This work serves as a step-ping stone towards scaling up regional captioning data and sheds light on exploring efficient ways to augment SAM with regional semantics. The project page, along with the associated code, can be accessed via the following link.

In this work, we aim to improve the 3D reasoning ability of Transformers in multi-view 3D human pose estimation. Recent works have focused on end-to-end learning-based transformer designs, which struggle to resolve geometric information accurately, particularly during occlusion. In-stead, we propose a novel hybrid model, MVGFormer, which has a series of geometric and appearance modules organized in an iterative manner. The geometry modules are learning-free and handle all viewpoint-dependent 3D tasks geometrically which notably improves the model's gener-alization ability. The appearance modules are learnable and are dedicated to estimating 2D poses from image signals end-to-end which enables them to achieve accurate es-timates even when occlusion occurs, leading to a model that is both accurate and generalizable to new cameras and geometries. We evaluate our approach for both in-domain and out-of-domain settings, where our model consistently outperforms state-of-the-art methods, and especially does so by a significant margin in the out-of-domain setting. We will release the code and models: https://github.com/XunshanMan/MVGFormer.

Existing diffusion-based video editing models have made gorgeous advances for editing attributes of a source video over time but struggle to manipulate the motion information while preserving the original protagonist's appearance and background. To address this, we propose MotionEditor, the first diffusion model for video motion editing. MotionEditor incorporates a novel content-aware motion adapter into ControlNet to capture temporal motion correspondence. While ControlNet enables direct generation based on skeleton poses, it encounters challenges when modifying the source motion in the inverted noise due to contradictory signals between the noise (source) and the condition (reference). Our adapter complements Control-Net by involving source content to transfer adapted control signals seamlessly. Further, we build up a two-branch ar-chitecture (a reconstruction branch and an editing branch) with a high-fidelity attention injection mechanism facilitating branch interaction. This mechanism enables the editing branch to query the key and value from the reconstruction branch in a decoupled manner, making the editing branch retain the original background and protagonist appearance. We also propose a skeleton alignment algorithm to address the discrepancies in pose size and position. Experiments demonstrate the promising motion editing ability of MotionEditor, both qualitatively and quantitatively. To the best of our knowledge, MotionEditor is the first to use diffusion models specifically for video motion editing, considering the origin dynamic background and camera movement.

The recent wave of AI-generated content has witnessed the great development and success of Text-to-Image (T2I) technologies. By contrast, Text-to- Video (T2V) still falls short of expectations though attracting increasing interest. Existing works either train from scratch or adapt large T2I model to videos, both of which are computation and re-source expensive. In this work, we propose a Simple Dif-fusion Adapter (SimDA) that fine-tunes only 24M out of I.IB parameters of a strong T2I model, adapting it to video generation in a parameter-efficient way. In particular, we turn the T2I model for T2V by designing light-weight spatial and temporal adapters for transfer learning. Besides, we change the original spatial attention to the proposed Latent-Shift Attention (LSA) for temporal consistency. With a similar model architecture, we further train a video super-resolution model to generate high-definition (1024 x 1024) videos. In addition to T2V generation in the wild, SimDA could also be utilized in one-shot video editing with only 2 minutes tuning. Doing so, our method could minimize the training effort with extremely few tunable parameters for model adaptation.

High-quality data is crucial for the pre-training performance of large language models.Unfortunately, existing quality filtering methods rely on a known high-quality dataset as reference, which can introduce potential bias and compromise diversity.In this paper, we propose ScalingFilter, a novel approach that evaluates text quality based on the perplexity difference between two language models trained on the same data, thereby eliminating the influence of the reference dataset in the filtering process.An theoretical analysis shows that ScalingFilter is equivalent to an inverse utilization of scaling laws.Through training models with 1.3B parameters on the same data source processed by various quality filters, we find ScalingFilter can improve zero-shot performance of pre-trained models in downstream tasks.To assess the bias introduced by quality filtering, we introduce semantic diversity, a metric of utilizing text embedding models for semantic representations.Extensive experiments reveal that semantic diversity is a reliable indicator of dataset diversity, and ScalingFilter achieves an optimal balance between downstream performance and semantic diversity.1

We introduce a highly performant 3D object detector for point clouds using the DETR framework. The prior attempts all end up with suboptimal results because they fail to learn accurate inductive biases from the limited scale of training data. In particular, the queries often attend to points that are far away from the target objects, violating the locality principle in object detection. To address the limitation, we introduce a novel 3D Vertex Relative Position Encoding (3DV-RPE) method which computes position encoding for each point based on its relative position to the 3D boxes predicted by the queries in each decoder layer, thus providing clear information to guide the model to focus on points near the objects, in accordance with the principle of locality. Furthermore, we have systematically refined our pipeline, including data normalization, to better align with the task requirements. Our approach demonstrates remarkable performance on the demanding ScanNetV2 benchmark, showcasing substantial enhancements over the prior state-of-the-art CAGroup3D. Specifically, we achieve an increase in $AP_{25}$ from $75.1\%$ to $77.8\%$ and in ${AP}_{50}$ from $61.3\%$ to $66.0\%$.

Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image. Previous methods have relied on domain-specific heuristics such as warping-based motion representation and 3D Morphable Models, which limit the naturalness and diversity of the generated avatars. In this work, we introduce GAIA (Generative AI for Avatar), which eliminates the domain priors in talking avatar generation. In light of the observation that the speech only drives the motion of the avatar while the appearance of the avatar and the background typically remain the same throughout the entire video, we divide our approach into two stages: 1) disentangling each frame into motion and appearance representations; 2) generating motion sequences conditioned on the speech and reference portrait image. We collect a large-scale high-quality talking avatar dataset and train the model on it with different scales (up to 2B parameters). Experimental results verify the superiority, scalability, and flexibility of GAIA as 1) the resulting model beats previous baseline models in terms of naturalness, diversity, lip-sync quality, and visual quality; 2) the framework is scalable since larger models yield better results; 3) it is general and enables different applications like controllable talking avatar generation and text-instructed avatar generation.

Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to out-of-domain tasks. However, current endeavors are hamstrung by an over-reliance on colossal models, exemplified by models with upwards of 3B parameters, and the necessity for an extensive corpus of visual data, often comprising a staggering 400B tokens. In this paper, we delve into the development of an efficient, autoregression-based vision model, innovatively architected to operate on a limited dataset. We meticulously demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding during the testing phase. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint, and a marked decrease in training data requirements, thereby paving the way for more sustainable and accessible advancements in the field of generalist vision models. The code is available at https://github.com/ggjy/DeLVM.

Graphic design conveys messages through the combination of text, images and other visual elements. Unstructured designs such as overloaded social media graphics may fail to communicate their intended messages effectively. To address this issue, layout grouping offers a solution by organizing design elements into perceptual groups. While most methods rely on heuristic Gestalt principles, they often lack the context modeling ability needed to handle complex layouts. In this work, we reformulate the layout grouping task as a set prediction problem. It uses Transformers to learn a set of group tokens at various hierarchies, enabling it to reason the membership of the elements more effectively. The self-attention mechanism in Transformers boosts its context modeling ability, which enables it to handle complex layouts more accurately. To reduce annotation costs, we also propose an unsupervised learning strategy that pre-trains on noisy pseudo-labels induced by a novel heuristic algorithm. This approach then bootstraps to self-refine the noisy labels, further improving the accuracy of our model. Our extensive experiments demonstrate the effectiveness of our method, which outperforms existing state-of-the-art approaches in terms of accuracy and efficiency.

In a wide range of dense prediction tasks, large-scale Vision Transformers have achieved state-of-the-art performance while requiring expensive computation. In contrast to most existing approaches accelerating Vision Transformers for image classification, we focus on accelerating Vision Transformers for dense prediction without any fine-tuning. We present two non-parametric operators specialized for dense prediction tasks, a token clustering layer to decrease the number of tokens for expediting and a token reconstruction layer to increase the number of tokens for recovering high-resolution. To accomplish this, the following steps are taken: i) token clustering layer is employed to cluster the neighboring tokens and yield low-resolution representations with spatial structures; ii) the following transformer layers are performed only to these clustered low-resolution tokens; and iii) reconstruction of high-resolution representations from refined low-resolution representations is accomplished using token reconstruction layer. The proposed approach shows promising results consistently on 6 dense prediction tasks, including object detection, semantic segmentation, panoptic segmentation, instance segmentation, depth estimation, and video instance segmentation. Additionally, we validate the effectiveness of the proposed approach on the very recent state-of-the-art open-vocabulary recognition methods. Furthermore, a number of recent representative approaches are benchmarked and compared on dense prediction tasks.

In this paper, we present a new sequence-to-sequence learning framework for visual tracking, dubbed SeqTrack. It casts visual tracking as a sequence generation problem, which predicts object bounding boxes in an autoregressive fashion. This is different from prior Siamese trackers and transformer trackers, which rely on designing complicated head networks, such as classification and regression heads. SeqTrack only adopts a simple encoder-decoder transformer architecture. The encoder extracts visual features with a bidirectional transformer, while the decoder generates a sequence of bounding box values autoregressively with a causal transformer. The loss function is a plain cross-entropy. Such a sequence learning paradigm not only simplifies tracking framework, but also achieves competitive performance on benchmarks. For instance, SeqTrack gets 72.5% AUC on LaSOT, establishing a new state-of-the-art performance. Code and models are available at https://github.com/microsoft/VideoX.

Human pose is typically represented by a coordinate vector of body joints or their heatmap embeddings. While easy for data processing, unrealistic pose estimates are admitted due to the lack of dependency modeling between the body joints. In this paper, we present a structured representation, named Pose as Compositional Tokens (PCT), to explore the joint dependency. It represents a pose by M discrete tokens with each characterizing a sub-structure with several interdependent joints (see Figure 1). The compositional design enables it to achieve a small reconstruction error at a low cost. Then we cast pose estimation as a classification task. In particular, we learn a classifier to predict the categories of the M tokens from an image. A pre-learned decoder network is used to recover the pose from the tokens without further post-processing. We show that it achieves better or comparable pose estimation results as the existing methods in general scenarios, yet continues to work well when occlusion occurs, which is ubiquitous in practice. The code and models are publicly available at https://github.com/Gengzigang/PCT.

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is important for the versatility of DETR, and it has been generalized to broader vision tasks. However, we note that there are few queries assigned as positive samples and the one-to-one set matching significantly reduces the training efficacy of positive samples. We propose a simple yet effective method based on a hybrid matching scheme that combines the original one-to-one matching branch with an auxiliary one-to-many matching branch during training. Our hybrid strategy has been shown to significantly improve accuracy. In inference, only the original one-to-one match branch is used, thus maintaining the end-to-end merit and the same inference efficiency of DETR. The method is namedℋ-DETR, and it shows that a wide range of representative DETR methods can be consistently improved across a wide range of visual tasks, including Deformable-DETR, PETRv2, PETR, and TransTrack, among others. Code is available at: https://github.com/HDETR.

Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. In this paper, we propose a family of high-speed vision transformers named Efficient ViT. We find that the speed of existing transformer models is commonly bounded by memory inefficient operations, especially the tensor reshaping and element-wise functions in MHSA. Therefore, we design a new building block with a sandwich layout, i.e., using a single memory-bound MHSA between efficient FFN layers, which improves memory efficiency while enhancing channel communication. Moreover, we discover that the attention maps share high similarities across heads, leading to computational redundancy. To address this, we present a cascaded group attention module feeding attention heads with different splits of the full feature, which not only saves computation cost but also improves attention diversity. Comprehensive experiments demonstrate EfficientViT outperforms existing efficient models, striking a good trade-off between speed and accuracy. For instance, our EfficientViT-M5 surpasses MobileNetV3-Large by 1.9% in accuracy, while getting 40.4% and 45.2% higher throughput on Nvidia V100 GPU and Intel Xeon CPU, respectively. Compared to the recent efficient model MobileViT-XXS, EfficientViT-M2 achieves 1.8% superior accuracy, while running$5.8\times/3.7\times$faster on the GPU/CPU, and$7.4\times faster$when converted to ONNX format. Code and models are available at here.

Masked image modeling (MIM) performs strongly in pretraining large vision Transformers (ViTs). However, small models that are critical for real-world applications can-not or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions. In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales. More importantly, to alternate among varying resolutions effectively, especially novel ones in testing, we propose a global-local positional embedding strategy that changes smoothly conditioned on input sizes. We conduct extensive experiments for image classification on ImageNet. The results provide strong quantitative evidence that ResFormer has promising scaling abilities towards a wide range of resolutions. For instance, ResFormer-B-MR achieves a Top-1 accuracy of 75.86% and 81.72% when evaluated on relatively low and high resolutions respectively (i.e., 96 and 640), which are 48% and 7.49% better than DeiT-B. We also demonstrate, moreover, ResFormer is flexible and can be easily extended to semantic segmentation, object detection and video action recognition.

This paper presents a method that effectively combines two prevalent visual recognition methods, i.e., image classification and contrastive language-image pre-training, dubbed iCLIP. Instead of naïve multi-task learning that use two separate heads for each task, we fuse the two tasks in a deep fashion that adapts the image classification to share the same formula and the same model weights with the language-image pre-training. To further bridge these two tasks, we propose to enhance the category names in image classification tasks using external knowledge, such as their descriptions in dictionaries. Extensive experiments show that the proposed method combines the advantages of two tasks well: the strong discrimination ability in image classification tasks due to the clean category labels, and the good zero-shot ability in CLIP tasks ascribed to the richer semantics in the text descriptions. In particular, it reaches 82.9% top-1 accuracy on IN-1K, and mean-while surpasses CLIP by 1.8%, with similar model size, on zero-shot recognition of Kornblith 12-dataset benchmark. The code and models are publicly available at https://github.com/weiyx16/iCLIP.

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pretrained models from two perspectives, the visualizations and the experiments, to uncover their key representational differences. From the visualizations, we find that MIM brings locality inductive bias to all layers of the trained models, but supervised models tend to focus locally at lower layers but more globally at higher layers. That may be the reason why MIM helps Vision Transformers that have a very large receptive field to optimize. Using MIM, the model can maintain a large diversity on attention heads in all layers. But for supervised models, the diversity on attention heads almost disappears from the last three layers and less diversity harms the fine-tuning performance. From the experiments, we find that MIM models can perform significantly better on geometric and motion tasks with weak semantics or fine-grained classification tasks, than their supervised counterparts. Without bells and whistles, a standard MIM pre-trained SwinV2-L could achieve state-of-the-art performance on pose estimation (78.9 AP on COCO test-dev and 78.0 AP on CrowdPose), depth estimation (0.287 RMSE on NYUv2 and 1.966 RMSE on KITTI), and video object tracking (70.7 SUC on LaSOT). For the semantic understanding datasets where the categories are sufficiently covered by the supervised pre-training, MIM models can still achieve highly competitive transfer performance. With a deeper understanding of MIM, we hope that our work can inspire new and solid research in this direction. Code will be available at https://github.com/zdaxie/MIM-DarkSecrets.

Scaling properties have been one of the central issues in self-supervised pre-training, especially the data scalability, which has successfully motivated the large-scale self-supervised pre-trained language models and endowed them with significant modeling capabilities. However, scaling properties seem to be unintentionally neglected in the recent trending studies on masked image modeling (MIM), and some arguments even suggest that MIM cannot benefit from large-scale data. In this work, we try to break down these preconceptions and systematically study the scaling behaviors of MIM through extensive experiments, with data ranging from 10% of ImageNet-1K to full ImageNet-22K, model parameters ranging from 49-million to one-billion, and training length ranging from 125K to 500K iterations. And our main findings can be summarized in two folds: 1) masked image modeling remains demanding large-scale data in order to scale up computes and model parameters; 2) masked image modeling cannot benefit from more data under a non-overfitting scenario, which diverges from the previous observations in self-supervised pre-trained language models or supervised pre-trained vision models. In addition, we reveal several intriguing properties in MIM, such as high sample efficiency in large MIM models and strong correlation between pre-training validation loss and transfer performance. We hope that our findings could deepen the understanding of masked image modeling and facilitate future developments on largescale vision models. Code and models will be available at https://github.com/microsoft/SimMIM.

Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been less explored. In this paper, we investigate the use of transformer models under the SSL setting for action recognition. To this end, we introduce SVFormer, which adopts a steady pseudo-labeling framework (i.e., EMA-Teacher) to cope with unlabeled video samples. While a wide range of data augmentations have been shown effective for semi-supervised image classification, they generally produce limited results for video recognition. We therefore introduce a novel augmentation strategy, Tube Token-Mix, tailored for video data where video clips are mixed via a mask with consistent masked tokens over the temporal axis. In addition, we propose a temporal warping augmentation to cover the complex temporal variation in videos, which stretches selected frames to various temporal durations in the clip. Extensive experiments on three datasets Kinetics-400, UCF-101, and HMDB-51 verify the advantage of SVFormer. In particular, SVFormer outperforms the state-of-the-art by 31.5% with fewer training epochs under the 1% labeling rate of Kinetics-400. Our method can hopefully serve as a strong benchmark and encourage future search on semi-supervised action recognition with Transformer networks. Code is released at https://github.com/ChenHsing/SVFormer.

This paper presents a new framework for open-vocabulary semantic segmentation with the pre-trained vision-language model, named Side Adapter Network (SAN). Our approach models the semantic segmentation task as a region recognition problem. A side network is attached to a frozen CLIP model with two branches: one for predicting mask proposals, and the other for predicting attention bias which is applied in the CLIP model to recognize the class of masks. This decoupled design has the benefit CLIP in recognizing the class of mask proposals. Since the attached side network can reuse CLIP features, it can be very light. In addition, the entire network can be trained end-to-end, allowing the side network to be adapted to the frozen CLIP model, which makes the predicted mask proposals CLIP-aware. Our approach is fast, accurate, and only adds a few additional trainable parameters. We evaluate our approach on multiple semantic segmentation benchmarks. Our method significantly outperforms other counterparts, with up to 18 times fewer trainable parameters and 19 times faster inference speed. Fig. 1 shows some visualization results on ImageNet. We hope our approach will serve as a solid baseline and help ease future research in open-vocabulary semantic segmentation.

Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting optimization directions between timesteps. To address this issue, we treat the diffusion training as a multi-task learning problem, and introduce a simple yet effective approach referred to as Min-SNR-γ. This method adapts loss weights of timesteps based on clamped signal-to-noise ratios, which effectively balances the conflicts among timesteps. Our results demonstrate a significant improvement in converging speed, 3.4× faster than previous weighting strategies. It is also more effective, achieving a new record FID score of 2.06 on the ImageNet 256 × 256 benchmark using smaller architectures than that employed in previous state-of-the-art. The code is available at https://github.com/TiankaiHang/Min-SNR-Diffusion-Training.

Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively refine themselves in a similar manner. However, we observe that the mask-attention pipeline usually leads to slow convergence due to low-recall initial instance masks. Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead. Through center regression, we effectively overcome the low-recall issue and perform cross-attention by imposing positional prior. To reach this goal, we develop a series of position-aware designs. First, we learn a spatial distribution of 3D locations as the initial position queries. They spread over the 3D space densely, and thus can easily capture the objects in a scene with a high recall. Moreover, we present relative position encoding for the cross-attention and iterative refinement for more accurate position queries. Experiments show that our approach converges 4× faster than existing work, sets a new state of the art on ScanNetv2 3D instance segmentation benchmark, and also demonstrates superior performance across various datasets. Code and models are available at https://github.com/dvlab-research/Mask-Attention-Free-Transformer.

This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality constraints, in contrast to previous leading DETR-based detectors that reintroduce architectural inductive biases of multi-scale and locality into the decoder. We show that two simple technologies are surprisingly effective within a plain design to compensate for the lack of multi-scale feature maps and locality constraints. The first is a box-to-pixel relative position bias (BoxRPB) term added to the cross-attention formulation, which well guides each query to attend to the corresponding object region while also providing encoding flexibility. The second is masked image modeling (MIM)-based backbone pre-training which helps learn representation with fine-grained localization ability and proves crucial for remedying dependencies on the multi-scale feature maps. By incorporating these technologies and recent advancements in training and problem formation, the improved "plain" DETR showed exceptional improvements over the original DETR detector. By leveraging the Object365 dataset for pre-training, it achieved 63.9 mAP accuracy using a Swin-L backbone, which is highly competitive with state-of-the-art detectors which all heavily rely on multi-scale feature maps and region-based feature extraction. Code will be available at https://github.com/impiga/Plain-DETR.

We introduce AiT, a unified output representation for various vision tasks, which is a crucial step towards general-purpose vision task solvers. Despite the challenges posed by the high-dimensional and task-specific outputs, we showcase the potential of using discrete representation (VQVAE) to model the dense outputs of many computer vision tasks as a sequence of discrete tokens. This is inspired by the established ability of VQ-VAE to conserve the structures spanning multiple pixels using few discrete codes. To that end, we present a modified shallower architecture for VQ-VAE that improves efficiency while keeping prediction accuracy. Our approach also incorporates uncertainty into the decoding process by using a soft fusion of the codebook entries, providing a more stable training process, which notably improved prediction accuracy. Our evaluation of AiT on depth estimation and instance segmentation tasks, with both continuous and discrete labels, demonstrates its superiority compared to other unified models. The code and models are available at https://github.com/SwinTransformer/AiT.

Contrastive language-image pretraining (CLIP) has demonstrated remarkable success in various image tasks. However, how to extend CLIP with effective temporal modeling is still an open and crucial problem. Existing factorized or joint spatial-temporal modeling trades off between the efficiency and performance. While modeling temporal information within straight through tube is widely adopted in literature, we find that simple frame alignment already provides enough essence without temporal attention. To this end, in this paper, we proposed a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance. Specifically, for a frame pair, an interactive point is predicted in each frame, serving as a mutual information rich region. By enhancing the features around the interactive point, two frames are implicitly aligned. The aligned features are then pooled into a single token, which is leveraged in the subsequent spatial self-attention. Our method allows eliminating the costly or insufficient temporal self-attention in video. Extensive experiments on benchmarks demonstrate the superiority and generality of our module. Particularly, the proposed ILA achieves a top-1 accuracy of 88.7% on Kinetics-400 with much fewer FLOPs compared with Swin-L and ViViT-H. Code is released at https://github.com/Francis-Rings/ILA.

CLIP models have demonstrated impressively high zero-shot recognition accuracy, however, their fine-tuning performance on downstream vision tasks is sub-optimal. Contrarily, masked image modeling (MIM) performs exceptionally for fine-tuning on downstream tasks, despite the absence of semantic labels during training. We note that the two tasks have different ingredients: image-level targets versus token-level targets, a cross-entropy loss versus a regression loss, and full-image inputs versus partial-image inputs. To mitigate the differences, we introduce a classical feature map distillation framework, which can simultaneously inherit the semantic capability of CLIP models while constructing a task incorporated key ingredients of MIM. Experiments suggest that the feature map distillation approach significantly boosts the fine-tuning performance of CLIP models on several typical down-stream vision tasks. We also observe that the approach yields new CLIP representations which share some diagnostic properties with those of MIM. Furthermore, the feature map distillation approach generalizes to other pre-training models, such as DINO, DeiT and SwinV2-G, reaching a new record of 64.2 mAP on COCO object detection with +1.1 improvement. The code and models are publicly available at https://github.com/SwinTransformer/Feature-Distillation.

In this paper, we propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models. The method introduces two core techniques: affinity mimicking and weight inheritance. Affinity mimicking explores the interaction between modalities during distillation, enabling student models to mimic teachers’ behavior of learning cross-modal feature alignment in a visual-linguistic affinity space. Weight inheritance transmits the pre-trained weights from the teacher models to their student counterparts to improve distillation efficiency. Moreover, we extend the method into a multi-stage progressive distillation to mitigate the loss of informative weights during extreme compression. Comprehensive experiments demonstrate the efficacy of TinyCLIP, showing that it can reduce the size of the pre-trained CLIP ViT-B/32 by 50%, while maintaining comparable zero-shot performance. While aiming for comparable performance, distillation with weight inheritance can speed up the training by 1.4 - 7.8× compared to training from scratch. Moreover, our TinyCLIP ViT-8M/16, trained on YFCC-15M, achieves an impressive zero-shot top-1 accuracy of 41.1% on ImageNet, surpassing the original CLIP ViT-B/16 by 3.5% while utilizing only 8.9% parameters. Finally, we demonstrate the good transferability of TinyCLIP in various downstream tasks. Code and models will be open-sourced at aka.ms/tinyclip.

In vision-language modeling, image token removal is an efficient augmentation technique to reduce the cost of encoding image features. The CLIP-style models, however, have been found to be negatively impacted by this technique. We hypothesize that removing a large portion of image tokens may inadvertently destroy the semantic information associated to a given text description, resulting in misaligned paired data in CLIP training. To address this issue, we propose an attentive token removal approach, which retains a small number of tokens that have a strong semantic correlation to the corresponding text description. The correlation scores are dynamically evaluated through an EMA-updated vision encoder. Our method, termed attentive mask CLIP, outperforms original CLIP and CLIP variant with random token removal while saving the training time. In addition, our approach also enables efficient multi-view contrastive learning. Experimentally, by training ViT-B on YFCC-15M dataset, our approach achieves 43.9% top-1 accuracy on ImageNet-1K zero-shot classification, 62.7/42.1 and 38.0/23.2 I2T/T2I retrieval accuracy on Flickr30K and MS COCO, outperforming SLIP by +1.1%, +5.5/+0.9, and +4.4/+1.3, respectively, while being 2.30× faster. An efficient version of our approach runs 1.16× faster than the plain CLIP model, while achieving significant gains of +5.3%, +11.3/+8.0, and +9.5/+4.9 on these benchmarks, respectively. Code will be release in https://github.com/microsoft/A-CLIP.

The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we identify the small data pitfall that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K. Specifically, we show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1%, 84.3%, and 85.0% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at https://github.com/Hao840/vanillaKD.

Knowledge distillation (KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family, particularly the hint-based approaches. By using centered kernel alignment (CKA) to compare the learned features between heterogeneous teacher and student models, we observe significant feature divergence. This divergence illustrates the ineffectiveness of previous hint-based methods in cross-architecture distillation. To tackle the challenge in distilling heterogeneous models, we propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures. Specifically, we project intermediate features into an aligned latent space such as the logits space, where architecture-specific information is discarded. Additionally, we introduce an adaptive target enhancement scheme to prevent the student from being disturbed by irrelevant information. Extensive experiments with various architectures, including CNN, Transformer, and MLP, demonstrate the superiority of our OFA-KD framework in enabling distillation between heterogeneous architectures. Specifically, when equipped with our OFA-KD, the student models achieve notable performance improvements, with a maximum gain of 8.0% on the CIFAR-100 dataset and 0.7% on the ImageNet-1K dataset. PyTorch code and checkpoints can be found at https://github.com/Hao840/OFAKD.

Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given input image. A highly performant object detector requires accurate ranking for the bounding box predictions. For DETR-based detectors, the top-ranked bounding boxes suffer from less accurate localization quality due to the misalignment between classification scores and localization accuracy, thus impeding the construction of high-quality detectors. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs, combinedly called Rank-DETR. Our key contributions include: (i) a rank-oriented architecture design that can prompt positive predictions and suppress the negative ones to ensure lower false positive rates, as well as (ii) a rank-oriented loss function and matching cost design that prioritizes predictions of more accurate localization accuracy during ranking to boost the AP under high IoU thresholds. We apply our method to improve the recent SOTA methods (e.g., H-DETR and DINO-DETR) and report strong COCO object detection results when using different backbones such as ResNet-$50$, Swin-T, and Swin-L, demonstrating the effectiveness of our approach. Code is available at \url{https://github.com/LeapLabTHU/Rank-DETR}.

While language-guided image manipulation has made remarkable progress, the challenge of how to instruct the manipulation process faithfully reflecting human intentions persists. An accurate and comprehensive description of a manipulation task using natural language is laborious and sometimes even impossible, primarily due to the inherent uncertainty and ambiguity present in linguistic expressions. Is it feasible to accomplish image manipulation without resorting to external cross-modal language information? If this possibility exists, the inherent modality gap would be effortlessly eliminated. In this paper, we propose a novel manipulation methodology, dubbed ImageBrush, that learns visual instructions for more accurate image editing. Our key idea is to employ a pair of transformation images as visual instructions, which not only precisely captures human intention but also facilitates accessibility in real-world scenarios. Capturing visual instructions is particularly challenging because it involves extracting the underlying intentions solely from visual demonstrations and then applying this operation to a new image. To address this challenge, we formulate visual instruction learning as a diffusion-based inpainting problem, where the contextual information is fully exploited through an iterative process of generation. A visual prompting encoder is carefully devised to enhance the model's capacity in uncovering human intent behind the visual instructions. Extensive experiments show that our method generates engaging manipulation results conforming to the transformations entailed in demonstrations. Moreover, our model exhibits robust generalization capabilities on various downstream tasks such as pose transfer, image translation and video inpainting.

Recently, there has been an increasing interest in developing diffusion-based text-to-image generative models capable of generating coherent and well-formed visual text. In this paper, we propose a novel and efficient approach called GlyphControl to address this task. Unlike existing methods that rely on character-aware text encoders like ByT5 and require retraining of text-to-image models, our approach leverages additional glyph conditional information to enhance the performance of the off-the-shelf Stable-Diffusion model in generating accurate visual text. By incorporating glyph instructions, users can customize the content, location, and size of the generated text according to their specific requirements. To facilitate further research in visual text generation, we construct a training benchmark dataset called LAION-Glyph. We evaluate the effectiveness of our approach by measuring OCR-based metrics, CLIP score, and FID of the generated visual text. Our empirical evaluations demonstrate that GlyphControl outperforms the recent DeepFloyd IF approach in terms of OCR accuracy, CLIP score, and FID, highlighting the efficacy of our method.

The non-local network (NLNet) presents a pioneering approach for capturing long-range dependencies within an image, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by the non-local network are almost the same for different query positions. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further replace the one-layer transformation function of the non-local block by a two-layer bottleneck, which further reduces the parameter number considerably. The resulting network element, called the global context (GC) block, effectively models global context in a lightweight manner, allowing it to be applied at multiple layers of a backbone network to form a global context network (GCNet). Experiments show that GCNet generally outperforms NLNet on major benchmarks for various recognition tasks. The code and network configurations are available at https://github.com/xvjiarui/GCNet.

This article concentrates on open-vocabulary semantic segmentation, where a well optimized model is able to segment arbitrary categories that appear in an image. To achieve this goal, we present a novel framework termed Side Adapter Network, or SAN for short. Our design principles are three-fold: 1) Recent large-scale vision-language models (e.g. CLIP) show promising open-vocabulary image classification capability; it is training-economized to adapt a pre-trained CLIP model to open-vocabulary semantic segmentation. 2) Our SAN model should be both lightweight and effective in order to reduce the inference cost-to achieve this, we fuse the CLIP model's intermediate features to enhance the representation capability of the SAN model, and drive the CLIP model to focus on the informative areas of an image with the aid of the attention biases predicted by a side adapter network. 3) Our approach should empower mainstream segmentation architectures to have the capability of open-vocabulary segmentation-we present P-SAN and R-SAN, to support widely adopted pixel-wise segmentation and region-wise segmentation, respectively. Experimentally, our approach achieves state-of-the-art performance on 5 commonly used benchmarks while having much less trainable parameters and GFLOPs. For instance, our R-SAN outperforms previous best method OvSeg by +2.3 averaged mIoU across all benchmarks while using only 6% of trainable parameters and less than 1% of GFLOPs. In addition, we also conduct a comprehensive analysis of the open-vocabulary semantic segmentation datasets and verify the feasibility of transferring a well optimzied R-SAN model to video segmentation task.

We present techniques for scaling Swin Transformer [35] up to 3 billion parameters and making it capable of training with images of up to 1,536x1,536 resolution. By scaling up capacity and resolution, Swin Transformer sets new records on four representative vision benchmarks: 84.0% top-1 accuracy on ImageNet- V2 image classification, 63.1 / 54.4 box / mask mAP on COCO object detection, 59.9 mIoU on ADE20K semantic segmentation, and 86.8% top-1 accuracy on Kinetics-400 video action classification. We tackle issues of training instability, and study how to effectively transfer models pre-trained at low resolutions to higher resolution ones. To this aim, several novel technologies are proposed: 1) a residual post normalization technique and a scaled cosine attention approach to improve the stability of large vision models; 2) a log-spaced continuous position bias technique to effectively transfer models pre-trained at low-resolution images and windows to their higher-resolution counterparts. In addition, we share our crucial implementation details that lead to significant savings of GPU memory consumption and thus make it feasi-ble to train large vision models with regular GPUs. Using these techniques and self-supervised pre-training, we suc-cessfully train a strong 3 billion Swin Transformer model and effectively transfer it to various vision tasks involving high-resolution images or windows, achieving the state-of-the-art accuracy on a variety of benchmarks. Code is avail-able at https://github.com/microsoft/Swin-Transformer.

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video architecture is realized by adapting the Swin Transformer designed for the image domain, while continuing to leverage the power of pre-trained image models. Our approach achieves state-of-the-art accuracy on a broad range of video recognition benchmarks, including on action recognition (84.9 top-l accuracy on Kinetics-400 and 85.9 top-l accuracy on Kinetics-600 with ~20× less pre-training data and ~3× smaller model size) and temporal modeling (69.6 top-l accuracy on Something-Something v2).

This paper presents SimMIM, a simple framework for masked image modeling. We have simplified recently proposed relevant approaches, without the need for special designs, such as block-wise masking and tokenization via discrete VAE or clustering. To investigate what makes a masked image modeling task learn good representations, we systematically study the major components in our framework, and find that the simple designs of each component have revealed very strong representation learning performance: 1) random masking of the input image with a moderately large masked patch size (e.g., 32) makes a powerful pre-text task; 2) predicting RGB values of raw pixels by direct regression performs no worse than the patch classification approaches with complex designs; 3) the prediction head can be as light as a linear layer, with no worse performance than heavier ones. Using ViT-B, our approach achieves 83.8% top-1 fine-tuning accuracy on ImageNet-1K by pre-training also on this dataset, surpassing previous best approach by +0.6%. When applied to a larger model with about 650 million parameters, SwinV2-H, it achieves 87.1% top-1 accuracy on ImageNet-1K using only ImageNet-1K data. We also leverage this approach to address the data-hungry issue faced by large-scale model training, that a 3B model (Swin V2-G) is successfully trained to achieve state-of-the-art accuracy on four representative vision benchmarks using 40× less labelled data than that in previous practice (JFT-3B). The code is available at https://github.com/microsoft/SimMIM.

Temporal Knowledge Graph (TKG) reasoning has attracted increasing attention due to its enormous potential value, and the critical issue is how to model the complex temporal structure information effectively.Recent studies use the method of encoding graph snapshots into hidden vector space and then performing heuristic deductions, which perform well on the task of entity prediction.However, these approaches cannot predict when an event will occur, and have the following limitations: 1) there are many facts not related to the query that can confuse the model; 2) there exists information forgetting caused by long-term evolutionary processes.To this end, we propose a Graph Hawkes Transformer (GHT) for both TKG entity prediction and time prediction tasks in the future time.In GHT, there are two variants of Transformer, which capture the instantaneous structural information and temporal evolution information, respectively, and a new relational continuous-time encoding function to facilitate feature evolution with the Hawkes process.Extensive experiments on four public datasets demonstrate its superior performance, especially on long-term evolutionary tasks.

In the past few years, transformers have achieved promising performance on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds them from being deployed on edge devices such as cell phones and smart watches. Knowledge distillation is a widely used paradigm for compressing cumbersome architectures into compact students via transferring information. However, most of them are designed for convolutional neural networks (CNNs), which do not fully investigate the character of vision transformers. In this paper, we fully utilize the patch-level information and propose a fine-grained manifold distillation method for transformer-based networks. Specifically, we train a tiny student model to match a pre-trained teacher model in the patch-level manifold space. Then, we decouple the manifold matching loss into three terms with careful design to further reduce the computational costs for the patch relationship. Equipped with the proposed method, a DeiT-Tiny model containing 5M parameters achieves 76.5\% top-1 accuracy on ImageNet-1k, which is +2.0\% higher than previous distillation approaches. Transfer learning results on other classification benchmarks and downstream vision tasks also demonstrate the superiority of our method over the state-of-the-art algorithms.

Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in the large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the [\texttt{class}] token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification.In this paper, we focus on a more challenging problem, \ie, accelerating large-scale vision transformers for dense prediction without any additional re-training or fine-tuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a \emph{token clustering layer} to decrease the number of tokens and a \emph{token reconstruction layer} to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation. Accordingly, our method accelerates $40\%\uparrow$ FPS and saves $30\%\downarrow$ GFLOPs of ``Segmenter+ViT-L/$16$'' while maintaining $99.5\%$ of the performance on ADE$20$K without fine-tuning the official weights.

Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which is problematic in computer vision where tasks vary significantly in input/output format and the type of information that is of value. In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition. From this empirical analysis, our work answers the questions of what pretraining task fits best with this frozen setting, how to make the frozen setting more flexible to various downstream tasks, and the effect of larger model sizes. We additionally examine the upper bound of performance using a giant frozen pretrained model with 3 billion parameters (SwinV2-G) and find that it reaches competitive performance on a varied set of major benchmarks with only one shared frozen base network: 60.0 box mAP and 52.2 mask mAP on COCO object detection test-dev, 57.6 val mIoU on ADE20K semantic segmentation, and 81.7 top-1 accuracy on Kinetics-400 action recognition. With this work, we hope to bring greater attention to this promising path of freezing pretrained image models.

The Capsule Network is widely believed to be more robust than Convolutional Networks. However, there are no comprehensive comparisons between these two networks, and it is also unknown which components in the CapsNet affect its robustness. In this paper, we first carefully examine the special designs in CapsNet that differ from that of a ConvNet commonly used for image classification. The examination reveals five major new/different components in CapsNet: a transformation process, a dynamic routing layer, a squashing function, a marginal loss other than cross-entropy loss, and an additional class-conditional reconstruction loss for regularization. Along with these major differences, we conduct comprehensive ablation studies on three kinds of robustness, including affine transformation, overlapping digits, and semantic representation. The study reveals that some designs, which are thought critical to CapsNet, actually can harm its robustness, i.e., the dynamic routing layer and the transformation process, while others are beneficial for the robustness. Based on these findings, we propose enhanced ConvNets simply by introducing the essential components behind the CapsNet’s success. The proposed simple ConvNets can achieve better robustness than the CapsNet.

Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tasks requiring dense pixel predictions. In this paper, we introduce pixel-level pretext tasks for learning dense feature representations. The first task directly applies contrastive learning at the pixel level. We additionally propose a pixel-to-propagation consistency task that produces better results, even surpassing the state-of-the-art approaches by a large margin. Specifically, it achieves 60.2 AP, 41.4 / 40.5 mAP and 77.2 mIoU when transferred to Pascal VOC object detection (C4), COCO object detection (FPN / C4) and Cityscapes semantic segmentation using a ResNet-50 backbone network, which are 2.6 AP, 0.8 / 1.0 mAP and 1.0 mIoU better than the previous best methods built on instance-level contrastive learning. Moreover, the pixel-level pretext tasks are found to be effective for pre-training not only regular backbone networks but also head networks used for dense downstream tasks, and are complementary to instance-level contrastive methods. These results demonstrate the strong potential of defining pretext tasks at the pixel level, and suggest a new path forward in unsupervised visual representation learning. Code is available at https://github.com/zdaxie/PixPro.

Recently, directly detecting 3D objects from 3D point clouds has received increasing attention. To extract object representation from an irregular point cloud, existing methods usually take a point grouping step to assign the points to an object candidate so that a PointNet-like network could be used to derive object features from the grouped points. However, the inaccurate point assignments caused by the hand-crafted grouping scheme decrease the performance of 3D object detection.In this paper, we present a simple yet effective method for directly detecting 3D objects from the 3D point cloud. Instead of grouping local points to each object candidate, our method computes the feature of an object from all the points in the point cloud with the help of an attention mechanism in the Transformers [42], where the contribution of each point is automatically learned in the network training. With an improved attention stacking scheme, our method fuses object features in different stages and generates more accurate object detection results. With few bells and whistles, the proposed method achieves state-of-the-art 3D object detection performance on two widely used benchmarks, Scan-Net V2 and SUN RGB-D. The code and models are publicly available at https://github.com/zeliu98/Group-Free-3D

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text. To address these differences, we propose a hierarchical Transformer whose representation is computed with Shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it compatible with a broad range of vision tasks, including image classification (87.3 top-1 accuracy on ImageNet-1K) and dense prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO test-dev) and semantic segmentation (53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art by a large margin of +2.7 box AP and +2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones. The hierarchical design and the shifted window approach also prove beneficial for all-MLP architectures. The code and models are publicly available at https://github.com/microsoft/Swin-Transformer.

This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods. The end-to-end training gradually improves pseudo label qualities during the curriculum, and the more and more accurate pseudo labels in turn benefit object detection training. We also propose two simple yet effective techniques within this framework: a soft teacher mechanism where the classification loss of each unlabeled bounding box is weighed by the classification score produced by the teacher network; a box jittering approach to select reliable pseudo boxes for the learning of box regression. On the COCO benchmark, the proposed approach outperforms previous methods by a large margin under various labeling ratios, i.e. 1%, 5% and 10%. Moreover, our approach proves to perform also well when the amount of labeled data is relatively large. For example, it can improve a 40.9 mAP baseline detector trained using the full COCO training set by +3.6 mAP, reaching 44.5 mAP, by leveraging the 123K unlabeled images of COCO. On the state-of-the-art Swin Transformer based object detector (58.9 mAP on test-dev), it can still significantly improve the detection accuracy by +1.5 mAP, reaching 60.4 mAP, and improve the instance segmentation accuracy by +1.2 mAP, reaching 52.4 mAP. Further incorporating with the Object365 pre-trained model, the detection accuracy reaches 61.3 mAP and the instance segmentation accuracy reaches 53.0 mAP, pushing the new state-of-the-art. The code and models will be made publicly available at https://github.com/microsoft/SoftTeacher.

Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution. Existing approaches almost all neglect this problem, and treat categories equally. Some popular approaches such as consistency regularization or pseudo-labeling may even harm the learning of under-performing categories, that the predictions or pseudo labels of these categories could be too inaccurate to guide the learning on the unlabeled data. In this paper, we look into this problem, and propose a novel framework for semi-supervised semantic segmentation, named adaptive equalization learning (AEL). AEL adaptively balances the training of well and badly performed categories, with a confidence bank to dynamically track category-wise performance during training. The confidence bank is leveraged as an indicator to tilt training towards under-performing categories, instantiated in three strategies: 1) adaptive Copy-Paste and CutMix data augmentation approaches which give more chance for under-performing categories to be copied or cut; 2) an adaptive data sampling approach to encourage pixels from under-performing category to be sampled; 3) a simple yet effective re-weighting method to alleviate the training noise raised by pseudo-labeling. Experimentally, AEL outperforms the state-of-the-art methods by a large margin on the Cityscapes and Pascal VOC benchmarks under various data partition protocols. Code is available at https://github.com/hzhupku/SemiSeg-AEL.

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream task. We argue that this could be sub-optimal and thus advocate a design principle which encourages alignment between the self-supervised pretext task and the downstream task. In this paper, we follow this principle with a pretraining method specifically designed for the task of object detection. We attain alignment in the following three aspects: 1) object-level representations are introduced via selective search bounding boxes as object proposals; 2) the pretraining network architecture incorporates the same dedicated modules used in the detection pipeline (e.g. FPN); 3) the pretraining is equipped with object detection properties such as object-level translation invariance and scale invariance. Our method, called Selective Object COntrastive learning (SoCo), achieves state-of-the-art results for transfer performance on COCO detection using a Mask R-CNN framework. Code is available at https://github.com/hologerry/SoCo.

We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that may be detrimental to training. In addition, it addresses localization noise and missing labels in human annotations by incorporating pseudo boxes that can compensate for these errors. Both of these MixTraining capabilities are made possible through bootstrapping on the detector, which can be used to predict the difficulty of training on a strong augmentation, as well as to generate reliable pseudo boxes thanks to the robustness of neural networks to labeling error. MixTraining is found to bring consistent improvements across various detectors on the COCO dataset. In particular, the performance of Faster R-CNN~\cite{ren2015faster} with a ResNet-50~\cite{he2016deep} backbone is improved from 41.7 mAP to 44.0 mAP, and the accuracy of Cascade-RCNN~\cite{cai2018cascade} with a Swin-Small~\cite{liu2021swin} backbone is raised from 50.9 mAP to 52.8 mAP.

How do humans recognize an object in a piece of video? Due to the deteriorated quality of single frame, it may be hard for people to identify an occluded object in this frame by just utilizing information within one image. We argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information. Recently, plenty of methods adopt the self-attention mechanisms to enhance the features in key frame with either global semantic information or local localization information. In this paper we introduce memory enhanced global-local aggregation (MEGA) network, which is among the first trials that takes full consideration of both global and local information. Furthermore, empowered by a novel and carefully-designed Long Range Memory (LRM) module, our proposed MEGA could enable the key frame to get access to much more content than any previous methods. Enhanced by these two sources of information, our method achieves state-of-the-art performance on ImageNet VID dataset. Code is available at https://github.com/Scalsol/mega.pytorch.

This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Unlike the state-of-the-art approaches which do instance discrimination in a dual-branch non-parametric fashion, PIC directly performs a one-branch parametric instance classification, revealing a simple framework similar to supervised classification and without the need to address the information leakage issue. We show that the simple PIC framework can be as effective as the state-of-the-art approaches, i.e. SimCLR and MoCo v2, by adapting several common component settings used in the state-of-the-art approaches. We also propose two novel techniques to further improve effectiveness and practicality of PIC: 1) a sliding-window data scheduler, instead of the previous epoch-based data scheduler, which addresses the extremely infrequent instance visiting issue in PIC and improves the effectiveness; 2) a negative sampling and weight update correction approach to reduce the training time and GPU memory consumption, which also enables application of PIC to almost unlimited training images. We hope that the PIC framework can serve as a simple baseline to facilitate future study. The code and network configurations are available at \url{https://github.com/bl0/PIC}.

Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement. We introduce verification tasks into the localization prediction of RepPoints, producing RepPoints v2, which proves consistent improvements of about 2.0 mAP over the original RepPoints on COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on the COCO \texttt{test-dev} by a single model. Moreover, we show that the proposed approach can more generally elevate other object detection frameworks as well as applications such as instance segmentation.

Existing object detection frameworks are usually built on a single format of object/part representation, i.e., anchor/proposal rectangle boxes in RetinaNet and Faster R-CNN, center points in FCOS and RepPoints, and corner points in CornerNet. While these different representations usually drive the frameworks to perform well in different aspects, e.g., better classification or finer localization, it is in general difficult to combine these representations in a single framework to make good use of each strength, due to the heterogeneous or non-grid feature extraction by different representations. This paper presents an attention-based decoder module similar as that in Transformer~\cite{vaswani2017attention} to bridge other representations into a typical object detector built on a single representation format, in an end-to-end fashion. The other representations act as a set of \emph{key} instances to strengthen the main \emph{query} representation features in the vanilla detectors. Novel techniques are proposed towards efficient computation of the decoder module, including a \emph{key sampling} approach and a \emph{shared location embedding} approach. The proposed module is named \emph{bridging visual representations} (BVR). It can perform in-place and we demonstrate its broad effectiveness in bridging other representations into prevalent object detection frameworks, including RetinaNet, Faster R-CNN, FCOS and ATSS, where about $1.5\sim3.0$ AP improvements are achieved. In particular, we improve a state-of-the-art framework with a strong backbone by about $2.0$ AP, reaching $52.7$ AP on COCO test-dev. The resulting network is named RelationNet++. The code is available at \url{https://github.com/microsoft/RelationNet2}.

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content. To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. The modeling power is enhanced through a more comprehensive integration of deformable convolution within the network, and by introducing a modulation mechanism that expands the scope of deformation modeling. To effectively harness this enriched modeling capability, we guide network training via a proposed feature mimicking scheme that helps the network to learn features that reflect the object focus and classification power of R-CNN features. With the proposed contributions, this new version of Deformable ConvNets yields significant performance gains over the original model and produces leading results on the COCO benchmark for object detection and instance segmentation.

The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling visual elements with varying spatial distributions. This paper presents a new image feature extractor, called the local relation layer, that adaptively determines aggregation weights based on the compositional relationship of local pixel pairs. With this relational approach, it can composite visual elements into higher-level entities in a more efficient manner that benefits semantic inference. A network built with local relation layers, called the Local Relation Network (LR-Net), is found to provide greater modeling capacity than its counterpart built with regular convolution on large-scale recognition tasks such as ImageNet classification.

Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is a key to the success of trackers. A good similarity score is expected to reflect multiple cues, e.g. appearance, location, and topology, over a long period of time. However, these cues are heterogeneous, making them hard to be combined in a unified network. As a result, existing methods usually encode them in separate networks or require a complex training approach. In this paper, we present a unified framework for similarity measurement based on spatial-temporal relation network which could simultaneously encode various cues and perform reasoning across both spatial and temporal domains. We also study the feature representation of a tracklet-object pair in depth, showing a proper design of the pair features can well empower the trackers. The resulting approach is named spatial-temporal relation networks (STRN). It runs in a feed-forward way and can be trained in an end-to-end manner. The state-of-the-art accuracy was achieved on all of the MOT15$\sim$17 benchmarks using public detection and online settings.

Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse localization of objects and leads to a correspondingly coarse extraction of object features. In this paper, we present RepPoints (representative points), a new finer representation of objects as a set of sample points useful for both localization and recognition. Given ground truth localization and recognition targets for training, RepPoints learn to automatically arrange themselves in a manner that bounds the spatial extent of an object and indicates semantically significant local areas. They furthermore do not require the use of anchors to sample a space of bounding boxes. We show that an anchor-free object detector based on RepPoints can be as effective as the state-of-the-art anchor-based detection methods, with 46.5 AP and 67.4 AP50 on the COCO test-dev detection benchmark, using ResNet-101 model. Code is available at https://github.com/microsoft/RepPoints.

Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era. All state-of-the-art object detection systems still rely on recognizing object instances individually, without exploiting their relations during learning. This work proposes an object relation module. It processes a set of objects simultaneously through interaction between their appearance feature and geometry, thus allowing modeling of their relations. It is lightweight and in-place. It does not require additional supervision and is easy to embed in existing networks. It is shown effective on improving object recognition and duplicate removal steps in the modern object detection pipeline. It verifies the efficacy of modeling object relations in CNN based detection. It gives rise to the first fully end-to-end object detector.

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from the target tasks, without additional supervision. The new modules can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard back-propagation, giving rise to deformable convolutional networks. Extensive experiments validate the performance of our approach. For the first time, we show that learning dense spatial transformation in deep CNNs is effective for sophisticated vision tasks such as object detection and semantic segmentation. The code is released at https://github.com/msracver/Deformable-ConvNets.

Image-based 3D reconstruction technology is widely used in different fields. The conventional algorithms are mainly based on stereo matching between two or more fixed cameras, and high accuracy can only be achieved using a large camera array, which is very expensive and inconvenient in many applications. Another popular choice is utilizing structure-from-motion methods for arbitrarily placed camera(s). However, due to too many degrees of freedom, its computational cost is heavy and its accuracy is rather limited. In this paper, we propose a novel depth estimation algorithm using a sliding camera system. By analyzing the geometric properties of the camera system, we design a camera pose initialization algorithm that can work satisfyingly with only a small number of feature points and is robust to noise. For pixels corresponding to different depths, an adaptive iterative algorithm is proposed to choose optimal frames for stereo matching, which can take advantage of continuously pose-changing imaging and save the time consumption amazingly too. The proposed algorithm can also be easily extended to handle less constrained situations (such as using a camera mounted on a moving robot or vehicle). Experimental results on both synthetic and real-world data have illustrated the effectiveness of the proposed algorithm.

Feature based image matching is essential for many computer vision applications. Recently, progressive methods which iteratively enrich the candidate matches and reject the wrong ones have attracted a lot of attentions due to its high precision/recall and efficiency. Its quality of enrichment and rejection relies heavily on the accuracy of the estimated local affine transformation and the capability of the geometric constraint constructed between features. In this paper, we propose a novel progressive feature matching algorithms based on triplet graph, which will produce a more general local affine transformation estimation method, and results in a powerful affine invariant constraint and efficient MRF optimization in rejecting mismatches. Experimental results on several challenging datasets have illustrated our method can achieve much higher precision/recall than existing methods.

Data in many image and video analysis tasks can be viewed as points drawn from multiple low-dimensional subspaces with each subspace corresponding to one category or class. One basic task for processing such kind of data is to separate the points according to the underlying subspace, referred to as subspace clustering. Extensive studies have been made on this subject, and nearly all of them use unconstrained subspace models, meaning the points can be drawn from everywhere of a subspace, to represent the data. In this paper, we attempt to do subspace clustering based on a constrained subspace assumption that the data is further restricted in the corresponding subspaces, e.g., belonging to a submanifold or satisfying the spatial regularity constraint. This assumption usually describes the real data better, such as differently moving objects in a video scene and face images of different subjects under varying illumination. A unified integer linear programming optimization framework is used to approach subspace clustering, which can be efficiently solved by a branch-and-bound (BB) method. We also show that various kinds of supervised information, such as subspace number, outlier ratio, pairwise constraints, size prior and etc., can be conveniently incorporated into the proposed framework. Experiments on real data show that the proposed method outperforms the state-of-the-art algorithms significantly in clustering accuracy. The effectiveness of the proposed method in exploiting supervised information is also demonstrated.

Subspace clustering is a powerful technology for clustering data according to the underlying subspaces. Representation based methods are the most popular subspace clustering approach in recent years. In this paper, we analyze the grouping effect of representation based methods in depth. In particular, we introduce the enforced grouping effect conditions, which greatly facilitate the analysis of grouping effect. We further find that grouping effect is important for subspace clustering, which should be explicitly enforced in the data self-representation model, rather than implicitly implied by the model as in some prior work. Based on our analysis, we propose the SMooth Representation (SMR) model. We also propose a new affinity measure based on the grouping effect, which proves to be much more effective than the commonly used one. As a result, our SMR significantly outperforms the state-of-the-art ones on benchmark datasets.

Normalized cut is a powerful method for image segmentation as well as data clustering. However, it does not perform well in challenging segmentation problems, such as segmenting objects in a complex background. Researchers have attempted to incorporate priors or constraints to handle such cases. Available priors in image segmentation problems may be hard or soft, unary or pairwise, but only hard must-link constraints and two-class settings are well studied. The main difficulties may lie in the following aspects: 1) the nontransitive nature of cannot-link constraints makes it hard to use such constraints in multi-class settings and 2) in multi-class or pairwise settings, the output labels have inconsistent representations with given priors, making soft priors difficult to use. In this paper, we propose novel algorithms, which can handle both hard and soft, both unary and pairwise priors in multi-class settings and provide closed form and efficient solutions. We also apply the proposed algorithms to the problem of object segmentation, producing good results by further introducing a spatial regularity term. Experiments show that the proposed algorithms outperform the state-of-the-art algorithms significantly in clustering accuracy. Other merits of the proposed algorithms are also demonstrated.

Video stabilization is important in many application fields, such as visual surveillance. Video stabilization and completion based on a single camera have been well studied in recent years, but it remains a very challenging problem. In this paper, we propose a novel framework to produce a stable high-resolution video for visual surveillance by using two cameras, in which one static camera serves to capture low-resolution wide-view-angle images, and the other is a pan-tilt-zoom camera to capture high-resolution images. Different with using a single camera, the interesting target can be detected and tracked more effectively and much more high-resolution information can be utilized for the stabilization and completion by using two videos from two cameras. A three-step stabilization approach is designed to deal with the resolution's discrepancy between two synchro videos and a four-stage completion strategy is taken to utilize more high-resolution information. Experimental results show that the proposed algorithm has a satisfying performance.

This paper studies the problem of spatio-temporal matching between trajectories from two videos of the same scene. In real applications, trajectories are usually extracted independently in different videos. So possibly a lot of trajectories stay “alone” (have no corresponding trajectory in the other video). In this paper, we propose a novel matching algorithm which can not only find the existing correspondences between trajectories, but also recover the corresponding trajectories of “alone” ones. First, we cast trajectory matching problem as an element recovering problem from a matrix constructed by matched trajectories of the two videos, which is naturally incomplete. Then, under affine camera assumption, we recover the matrix by sparse representation and ℓ1regularization techniques. Finally, the results are refined to the case of perspective projection by a local depths estimation procedure. Our algorithm can handle noisy, incomplete or outlying data. Experiments on both synthetic data and real videos show that the proposed method has good performance.

Recent years, image-based crack detection has attracted more and more attentions for its potential applications on the inspection, diagnosis, and maintenance of various products, e.g. metal workpiece, concrete structure, asphalt road and etc. Generally, the applications are inevitably confronted with noises such as non-uniform illuminated conditions, shadings, stains and nature textures. To ease the problem, traditional methods usually focused on a special application and are carried out with strictly controlled image acquisition environments or an adhoc preprocessing procedure. In this paper, we propose a general crack detection method which can deal with various products as well as the noises in a unified fashion, and even with the same parameters. The method partitions an image into overlapped small grid cells and determines whether the cells contain cracks using a well designed feature descriptor. Experiments using real images of various products show the effectiveness of the proposed feature as well as the method.

Motion segmentation is an important topic in computer vision. In this paper, we study the problem of multi-body motion segmentation under the affine camera model. We use a mixture of subspace model to describe the multi-body motions. Then the motion segmentation problem is formulated as an MAP estimation problem with model complexity penalty. With several candidate motion models, the problem can be naturally converted into a linear programming problem, which guarantees a global optimality. The main advantages of our algorithm include: It needs no priori on the number of motions and it has comparable high segmentation accuracy with the best of motion-number-known algorithms. Experiments on benchmark data sets illustrate these points.