Related papers: CaFT: Clustering and Filter on Tokens of Transform…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose…

Vision transformers (ViTs) are changing the landscape of object detection approaches. A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with…

The research on recognizing the most discriminative regions provides referential information for weakly supervised object localization with only image-level annotations. However, the most discriminative regions usually conceal the other…

Pre-training convolutional neural networks with weakly-supervised and self-supervised strategies is becoming increasingly popular for several computer vision tasks. However, due to the lack of strong discriminative signals, these learned…

Video salient object detection models trained on pixel-wise dense annotation have achieved excellent performance, yet obtaining pixel-by-pixel annotated datasets is laborious. Several works attempt to use scribble annotations to mitigate…

Convolutional blocks have played a crucial role in advancing medical image segmentation by excelling in dense prediction tasks. However, their inability to effectively capture long-range dependencies has limited their performance.…

Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this paper, we propose a…

Despite the recent success in many applications, the high computational requirements of vision transformers limit their use in resource-constrained settings. While many existing methods improve the quadratic complexity of attention, in most…

Face clustering is a useful tool for applications like automatic face annotation and retrieval. The main challenge is that it is difficult to cluster images from the same identity with different face poses, occlusions, and image quality.…

Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains. To address the problem of poor detail…

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in…

Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space.…

The generalization problem is broadly recognized as a critical challenge in detecting deepfakes. Most previous work believes that the generalization gap is caused by the differences among various forgery methods. However, our investigation…

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

Weakly supervised semantic segmentation (WSSS) with only image-level supervision is a challenging task. Most existing methods exploit Class Activation Maps (CAM) to generate pixel-level pseudo labels for supervised training. However, due to…

Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks…

Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from images captured at different places and times. Recently, object Re-ID has achieved great success with the advances of Vision Transformers (ViT). However,…

In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set…

Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling…