Related papers: Near, far: Patch-ordering enhances vision foundati…

The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…

While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To address this, we propose Pixel-level Correspondence (PiCo), a…

In this paper, we focus on unsupervised learning for Video Object Segmentation (VOS) which learns visual correspondence (i.e., the similarity between pixel-level features) from unlabeled videos. Previous methods are mainly based on the…

We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes. It is a challenging problem to estimate dense pixel correspondences between images depicting different scenes or instances of the same…

Vision transformer has demonstrated promising performance on challenging computer vision tasks. However, directly training the vision transformers may yield unstable and sub-optimal results. Recent works propose to improve the performance…

Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…

Feature representation via self-supervised learning has reached remarkable success in image-level contrastive learning, which brings impressive performances on image classification tasks. While image-level feature representation mainly…

We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO). DPVO uses a novel recurrent network architecture designed for tracking image patches across time. Recent approaches to VO have…

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…

Neural Radiance Fields (NeRF) has demonstrated remarkable 3D reconstruction capabilities with dense view images. However, its performance significantly deteriorates under sparse view settings. We observe that learning the 3D consistency of…

In this paper, we propose a simple yet effective transformer framework for self-supervised learning called DenseDINO to learn dense visual representations. To exploit the spatial information that the dense prediction tasks require but…

Self-supervised pre-training and transformer-based networks have significantly improved the performance of object detection. However, most of the current self-supervised object detection methods are built on convolutional-based…

In direct imaging at high contrast, the bright glare produced by the host star makes the detection and the characterization of sub-stellar companions particularly challenging. In spite of the use of an extreme adaptive optics system…

Thin, reflective objects such as forks and whisks are common in our daily lives, but they are particularly challenging for robot perception because it is hard to reconstruct them using commodity RGB-D cameras or multi-view stereo…

Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching models is challenging because of its deterministic sampling…

Neural Architecture Search (NAS) is widely used to automatically obtain the neural network with the best performance among a large number of candidate architectures. To reduce the search time, zero-shot NAS aims at designing training-free…

Recent years have witnessed the success of deep learning on the visual sound separation task. However, existing works follow similar settings where the training and testing datasets share the same musical instrument categories, which to…

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…