Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised trackers struggle when visual cues become ambiguous, limiting their scalability and generalization without extensive labeled data. We find that pre-trained video diffusion models inherently learn motion representations suitable for tracking without task-specific training. This ability arises because their denoising process isolates motion in early, high-noise stages, distinct from later appearance refinement. Capitalizing on this discovery, our self-supervised tracker significantly improves performance in distinguishing visually similar objects, an underexplored failure point for existing methods. Our method achieves up to a 6-point improvement over recent self-supervised approaches on established benchmarks and our newly introduced tests focused on tracking visually similar items. Visualizations confirm that these diffusion-derived motion representations enable robust tracking of even identical objects across challenging viewpoint changes and deformations. Project page: \small{\url{https://chenshuang-zhang.github.io/projects/ted}}.

We establish rigorous benchmarks for visual perception robustness. Synthetic images such as ImageNet-C, ImageNet-9, and Stylized ImageNet provide specific type of evaluation over synthetic corruptions, backgrounds, and textures, yet those robustness benchmarks are restricted in specified variations and have low synthetic quality. In this work, we introduce generative model as a data source for synthesizing hard images that benchmark deep models' robustness. Leveraging diffusion models, we are able to generate images with more diversified backgrounds, textures, and materials than any prior work, where we term this benchmark as ImageNet-D. Experimental results show that ImageNet-D results in a significant accuracy drop to a range of vision models, from the standard ResNet visual classifier to the latest foundation models like CLIP and MiniGPT-4, significantly reducing their accuracy by up to 60%. Our work suggests that diffusion models can be an effective source to test vision models. The code and dataset are available at https://github.com/chenshuang-zhang/imagenet_d.

This paper addresses the challenges in multi-target domain adaptive (MTDA) for semantic segmentation, aiming to learn a single model capable of adapting to multi-target domains. Existing methods solely focus on visual appearance (style) discrepancies, overlooking contextual variations across multi-target domains, resulting in limited performance. We propose a novel approach termed Masking-augmented Collaborative Domain Congregation (MacDC) to handle both style gap and contextual gap among multi-target domains. MacDC achieves this goal by generating image-level and region-level intermediate domains among multi-target domains. To further strengthen contextual alignment, MacDC applies multi-context masking that enforces the model’s understanding of diverse contexts. Notably, MacDC directly learns a single model for multi-target domain adaptation, significantly reducing training times and model parameters. Despite its simplicity, MacDC demonstrates superior performance compared to state-of-the-art MTDA segmentation methods on the syn-to-real and real-to-real benchmarks.

With the increasing popularity of masked autoencoders, self-supervised learning (SSL) in vision undertakes a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction have become a de facto standard SSL practice in NLP (e.g., BERT). By contrast, early attempts at generative methods in vision have been outperformed by their discriminative counterparts (like contrastive learning). However, the success of masked image modeling has revived the autoencoder-based visual pretraining method. As a milestone to bridge the gap with BERT in NLP, masked autoencoder in vision has attracted unprecedented attention. This work conducts a survey on masked autoencoders for visual SSL.