This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs and task-specific pretraining, our research finds that general-purpose models pretrained on videos can be readily transferred to multi-view problems with minimal adaptation. The core insight is that general-purpose attention between patches learns temporal and spatial information for geometric reasoning. We demonstrate that appending a linear decoder to the Transformer backbone produces satisfactory results, and iterative refinement can further elevate performance to state-of-the-art levels. This conceptually simple approach achieves top cross-dataset generalization results for optical flow estimation with end-point error (EPE) of 0.69, 1.78, and 3.15 on the Sintel clean, Sintel final, and KITTI datasets, respectively. Our method additionally establishes a new record on the online test benchmark with EPE values of 0.79, 1.88, and F1 value of 3.79. Applications to 3D depth estimation and stereo matching also show strong performance, illustrating the versatility of video-pretrained models in addressing geometric vision tasks.

Diffusion policies are widely adopted in complex visuomotor tasks for their ability to capture multimodal action distributions. However, the multiple sampling steps required for action generation significantly harm real-time inference efficiency, which limits their applicability in real-time decision-making scenarios. Existing acceleration techniques either require retraining or degrade performance under low sampling steps. Here we propose Falcon, which mitigates this speed-performance trade-off and achieves further acceleration. The core insight is that visuomotor tasks exhibit sequential dependencies between actions. Falcon leverages this by reusing partially denoised actions from historical information rather than sampling from Gaussian noise at each step. By integrating current observations, Falcon reduces sampling steps while preserving performance. Importantly, Falcon is a training-free algorithm that can be applied as a plug-in to further improve decision efficiency on top of existing acceleration techniques. We validated Falcon in 48 simulated environments and 2 real-world robot experiments. demonstrating a 2-7x speedup with negligible performance degradation, offering a promising direction for efficient visuomotor policy design.

Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively regenerate only the intended editing areas. This results in (1) unnecessary computational costs and (2) a bias toward reconstructing non-editing regions, which compromises the quality of the intended edits. To resolve these limitations, we propose to formulate image editing as $\textbf{N}$ext $\textbf{E}$diting-token $\textbf{P}$rediction (NEP) based on autoregressive image generation, where only regions that need to be edited are regenerated, thus avoiding unintended modification to the non-editing areas. To enable any-region editing, we propose to pre-train an any-order autoregressive text-to-image (T2I) model. Once trained, it is capable of zero-shot image editing and can be easily adapted to NEP for image editing, which achieves a new state-of-the-art on widely used image editing benchmarks. Moreover, our model naturally supports test-time scaling (TTS) through iteratively refining its generation in a zero-shot manner.

This article presents a simple yet effective two-stage framework for semi-supervised medical image segmentation. Unlike prior state-of-the-art semi-supervised segmentation methods that predominantly rely on pseudo supervision directly on predictions, such as consistency regularization and pseudo labeling, our key insight is to explore the feature representation learning with labeled and unlabeled (i.e., pseudo labeled) images to regularize a more compact and better-separated feature space, which paves the way for low-density decision boundary learning and therefore enhances the segmentation performance. A stage-adaptive contrastive learning method is proposed, containing a boundary-aware contrastive loss that takes advantage of the labeled images in the first stage, as well as a prototype-aware contrastive loss to optimize both labeled and pseudo labeled images in the second stage. To obtain more accurate prototype estimation, which plays a critical role in prototype-aware contrastive learning, we present an aleatoric uncertainty-aware method to generate higher quality pseudo labels. Aleatoric-uncertainty adaptive (AUA) adaptively regularizes prediction consistency by taking advantage of image ambiguity, which, given its significance, is underexplored by existing works. Our method achieves the best results on three public medical image segmentation benchmarks.

Self-supervised representation learning follows a paradigm of withholding some part of the data and tasking the network to predict it from the remaining part. Among many techniques, data augmentation lies at the core for creating the information gap. Towards this end, masking has emerged as a generic and powerful tool where content is withheld along the sequential dimension, e.g., spatial in images, temporal in audio, and syntactic in language. In this paper, we explore the orthogonal channel dimension for generic data augmentation by exploiting precision redundancy. The data for each channel is quantized through a non-uniform quantizer, with the quantized value sampled randomly within randomly sampled quantization bins. From another perspective, quantization is analogous to channel-wise masking, as it removes the information within each bin, but preserves the information across bins. Our approach significantly surpasses existing generic data augmentation methods, while showing on par performance against modality-specific augmentations. We comprehensively evaluate our approach on vision, audio, 3D point clouds, as well as the DABS benchmark which is comprised of various data modalities. The code is available at https://github.com/microsoft/random_quantize.

The purpose of federated learning is to enable multiple clients to jointly train a machine learning model without sharing data. However, the existing methods for training an image segmentation model have been based on an unrealistic assumption that the training set for each local client is annotated in a similar fashion and thus follows the same image supervision level. To relax this assumption, in this work, we propose a label-agnostic unified federated learning framework, named FedMix, for medical image segmentation based on mixed image labels. In FedMix, each client updates the federated model by integrating and effectively making use of all available labeled data ranging from strong pixel-level labels, weak bounding box labels, to weakest image-level class labels. Based on these local models, we further propose an adaptive weight assignment procedure across local clients, where each client learns an aggregation weight during the global model update. Compared to the existing methods, FedMix not only breaks through the constraint of a single level of image supervision but also can dynamically adjust the aggregation weight of each local client, achieving rich yet discriminative feature representations. Experimental results on multiple publicly-available datasets validate that the proposed FedMix outperforms the state-of-the-art methods by a large margin. In addition, we demonstrate through experiments that FedMix is extendable to multi-class medical image segmentation and much more feasible in clinical scenarios. The code is available at: https://github.com/Jwicaksana/FedMix.

This study investigates barely-supervised medical image segmentation where only few labeled data, i.e., single-digit cases are available. We observe the key limitation of the existing state-of-the-art semi-supervised solution cross pseudo supervision is the unsatisfactory precision of foreground classes, leading to a degenerated result under barely-supervised learning. In this paper, we propose a novel Compete-to-Win method (ComWin) to enhance the pseudo label quality. In contrast to directly using one model’s predictions as pseudo labels, our key idea is that high-quality pseudo labels should be generated by comparing multiple confidence maps produced by different networks to select the most confident one (a compete-to-win strategy). To further refine pseudo labels at near-boundary areas, an enhanced version of ComWin, namely, ComWin$^{+}$, is proposed by integrating a boundary-aware enhancement module. Experiments show that our method can achieve the best performance on three public medical image datasets for cardiac structure segmentation, pancreas segmentation and colon tumor segmentation, respectively. The source code is now available athttps://github.com/Huiimin5/comwin.

Recognition and detection of interactive actions performed by multiple persons have a wide range of real-world applications. Existing studies on the human activity analysis focus mainly on classifying video clips of simple actions performed by a single person, whereas the problem of understanding complex human activities with causal relationships between two people has not been sufficiently addressed yet. In this paper, we employ systematically organized skeleton features enhanced with directional features, and utilize sparse-group lasso to automatically choose discriminative factors that help in dealing with interactive action recognition and real-time detection tasks. Experiments on two person interaction datasets demonstrate the superiority of our approach to the state-of-the-art methods.

Anomaly detection and localization in surveillance videos have attracted broad attention in both academic and industry for its importance to public safety, which however remain challenging. In this demonstration, we propose an anomaly detection algorithm called 2stream-VAE/GAN by embedding VAE/GAN in a two-stream architecture. By taking both spatial and temporal information into consideration, normality can be captured and anomaly detection can be achieved. With an outlier detection rule, the system automatically locates anomaly based on a pre-trained model, which suits well for both streaming and local videos.