Related papers: The Missing Point in Vision Transformers for Unive…
Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a…
Semantic image segmentation is an important computer vision task that is difficult because it consists of both recognition and segmentation. The task is often cast as a structured output problem on an exponentially large output-space, which…
Vision Transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it remains unclear how to adapt these pre-trained…
Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…
This work presents a systematic investigation into modernizing Vision Transformer backbones by leveraging architectural advancements from the past five years. While preserving the canonical Attention-FFN structure, we conduct a…
Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be…
The recently proposed data augmentation TransMix employs attention labels to help visual transformers (ViT) achieve better robustness and performance. However, TransMix is deficient in two aspects: 1) The image cropping method of TransMix…
Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks and result in comparable performance to convolutional neural networks (CNN), which have been studied and adopted…
Standard approaches for video recognition usually operate on the full input videos, which is inefficient due to the widely present spatio-temporal redundancy in videos. Recent progress in masked video modelling, i.e., VideoMAE, has shown…
What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale…
Few-shot segmentation has been attracting a lot of attention due to its effectiveness to segment unseen object classes with a few annotated samples. Most existing approaches use masked Global Average Pooling (GAP) to encode an annotated…
Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Since the real-world is actually video-based rather than…
Segmentation maps of medical images annotated by medical experts contain rich spatial information. In this paper, we propose to decompose annotation maps to learn disentangled and richer feature transforms for segmentation problems in…
Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output…
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the…
We propose an embarrassingly simple point annotation scheme to collect weak supervision for instance segmentation. In addition to bounding boxes, we collect binary labels for a set of points uniformly sampled inside each bounding box. We…
Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this…
Vision Transformers (ViTs) have excelled in computer vision tasks but are memory-consuming and computation-intensive, challenging their deployment on resource-constrained devices. To tackle this limitation, prior works have explored…
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…
Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of…