相关论文: Which Tokens to Use? Investigating Token Reduction…

Vision Transformers (ViTs) deliver state-of-the-art accuracy but their quadratic attention cost and redundant computations severely hinder deployment on latency and resource-constrained platforms. Existing pruning approaches treat either…

Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most existing work estimates visual redundancy using a single…

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…

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…

Video understanding has made huge strides in recent years, relying largely on the power of transformers. As this architecture is notoriously expensive and video data is highly redundant, research into improving efficiency has become…

Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a function of the sequence length), dealing with ultra long…

Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs). However, existing approaches rely on predefined pruning…

Vision Transformers (ViTs) achieve strong performance in image classification but incur high computational costs from processing all image tokens. To reduce inference costs in large ViTs without compromising accuracy, we propose TinyDrop, a…

The most recent year has witnessed the success of applying the Vision Transformer (ViT) for image classification. However, there are still evidences indicating that ViT often suffers following two aspects, i) the high computation and the…

Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable of global information sharing. With the development of…

Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…

Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art…

Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC…

Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with…

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

While Transformers have rapidly gained popularity in various computer vision applications, post-hoc explanations of their internal mechanisms remain largely unexplored. Vision Transformers extract visual information by representing image…

Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually…

Vision Transformers (ViTs) have demonstrated strong performance across a wide range of vision tasks, yet their substantial computational and memory demands hinder efficient deployment on resource-constrained mobile and edge devices. Pruning…