相关论文: Data-independent Module-aware Pruning for Hierarch…

Pruning vision-language models (VLMs) for efficient deployment is challenging because compression can affect not only task utility but also visual grounding, often amplifying object hallucinations even at the same sparsity level. We present…

Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significantly to their high performance. However, it is known to incur…

Vision-Language Models (VLMs) encode images and videos into abundant tokens, which contain substantial redundancy and computation cost. While visual token pruning mitigates the issue, most existing methods lack insight into the intrinsic…

This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series…

The recently proposed Vision transformers (ViTs) have shown very impressive empirical performance in various computer vision tasks, and they are viewed as an important type of foundation model. However, ViTs are typically constructed with…

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Vision Transformers (ViTs) have achieved impressive results in computer vision by leveraging self-attention to model long-range dependencies. However, their emphasis on global context often comes at the expense of local feature extraction…

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…

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast…

Attention-based architectures have achieved superior performance in multivariate time series forecasting but are computationally expensive. Techniques such as patching and adaptive masking have been developed to reduce their sizes and…

The binarization of vision transformers (ViTs) offers a promising approach to addressing the trade-off between high computational/storage demands and the constraints of edge-device deployment. However, existing binary ViT methods often…

State-of-the-art text-to-image diffusion models (DMs) achieve remarkable quality, yet their massive parameter scale (8-11B) poses significant challenges for inferences on resource-constrained devices. In this paper, we present…

Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing multi-scale approaches alleviate this issue by integrating…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

Vision transformers (ViTs) quantization offers a promising prospect to facilitate deploying large pre-trained networks on resource-limited devices. Fully-binarized ViTs (Bi-ViT) that pushes the quantization of ViTs to its limit remain…

Model binarization can significantly compress model size, reduce energy consumption, and accelerate inference through efficient bit-wise operations. Although binarizing convolutional neural networks have been extensively studied, there is…

As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive field leads to quadratic computational cost. Another branch…

Convolutional Neural Networks (CNNs) for computer vision sometimes struggle with understanding images in a global context, as they mainly focus on local patterns. On the other hand, Vision Transformers (ViTs), inspired by models originally…