相关论文: Skip-Attention: Improving Vision Transformers by P…

Vision transformers have become one of the most important models for computer vision tasks. Although they outperform prior works, they require heavy computational resources on a scale that is quadratic to the number of tokens, $N$. This is…

The Vision Transformer (ViT) achieves remarkable accuracy across visual tasks but remains computationally expensive for edge deployment. This paper presents MicroViTv2, a lightweight Vision Transformer optimized for real-device efficiency.…

Transformers have achieved widespread and remarkable success, while the computational complexity of their attention modules remains a major bottleneck for vision tasks. Existing methods mainly employ 8-bit or 4-bit quantization to balance…

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the…

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce…

In recent years, Vision Transformers have attracted increasing interest from computer vision researchers. However, the advantage of these transformers over CNNs is only fully manifested when trained over a large dataset, mainly due to the…

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant…

The Vision Transformer (ViT) has demonstrated state-of-the-art performance in various computer vision tasks, but its high computational demands make it impractical for edge devices with limited resources. This paper presents MicroViT, 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…

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Vision transformer (ViT) has recently shown its strong capability in achieving comparable results to convolutional neural networks (CNNs) on image classification. However, vanilla ViT simply inherits the same architecture from the natural…

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

Attention-based transformer networks have demonstrated promising potential as their applications extend from natural language processing to vision. However, despite the recent improvements, such as sub-quadratic attention approximation and…

Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with simpler sequential modules is appealing, yet naive…

Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real…

We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed method takes token representations from the self-supervised ViT…

Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer…

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…