Related papers: VOLO: Vision Outlooker for Visual Recognition

The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources.…

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…

Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks. Despite recent successes of feedforward processing on the abstraction of concepts form raw images, the…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Self-attention in Transformers comes with a high computational cost because of their quadratic computational complexity, but their effectiveness in addressing problems in language and vision has sparked extensive research aimed at enhancing…

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks. However, these emerging architectures suffer from large model sizes and high computational…

The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range…

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Transformer, an attention-based encoder-decoder architecture, has not only revolutionized the field of natural language processing (NLP), but has also done some pioneering work in the field of computer vision (CV). Compared to convolutional…

Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various Computer Vision (CV) tasks. Building upon this paradigm, Vision…

Continual learning is a longstanding research topic due to its crucial role in tackling continually arriving tasks. Up to now, the study of continual learning in computer vision is mainly restricted to convolutional neural networks (CNNs).…

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…

Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with image size. Consequently, foundational…

Vision transformer (ViT) is an attention neural network architecture that is shown to be effective for computer vision tasks. However, compared to ResNet-18 with a similar number of parameters, ViT has a significantly lower evaluation…

Vision Transformers achieved outstanding performance in many computer vision tasks. Early Vision Transformers such as ViT and DeiT adopt global self-attention, which is computationally expensive when the number of patches is large. To…

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

Despite the rapid advancement of object detection algorithms, processing high-resolution images on embedded devices remains a significant challenge. Theoretically, the fully convolutional network architecture used in current real-time…