中文
相关论文

相关论文: Comprehensive Survey of Model Compression and Spee…

200 篇论文

Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still remain largely unknown. In this paper, we propose an…

计算机视觉与模式识别 · 计算机科学 2022-10-19 Van-Anh Nguyen , Khanh Pham Dinh , Long Tung Vuong , Thanh-Toan Do , Quan Hung Tran , Dinh Phung , Trung Le

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting…

计算机视觉与模式识别 · 计算机科学 2022-09-13 Zhuofan Zong , Kunchang Li , Guanglu Song , Yali Wang , Yu Qiao , Biao Leng , Yu Liu

We show how transformers can be used to vastly simplify neural video compression. Previous methods have been relying on an increasing number of architectural biases and priors, including motion prediction and warping operations, resulting…

计算机视觉与模式识别 · 计算机科学 2022-10-13 Fabian Mentzer , George Toderici , David Minnen , Sung-Jin Hwang , Sergi Caelles , Mario Lucic , Eirikur Agustsson

The development of deep learning algorithms has extensively empowered humanity's task automatization capacity. However, the huge improvement in the performance of these models is highly correlated with their increasing level of complexity,…

计算机视觉与模式识别 · 计算机科学 2024-01-19 Eduarda Caldeira , Pedro C. Neto , Marco Huber , Naser Damer , Ana F. Sequeira

Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \textit{extremely simple}…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Jin Gao , Shubo Lin , Shaoru Wang , Yutong Kou , Zeming Li , Liang Li , Congxuan Zhang , Xiaoqin Zhang , Yizheng Wang , Weiming Hu

Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Rajat Koner , Gagan Jain , Prateek Jain , Volker Tresp , Sujoy Paul

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…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Tobias Christian Nauen , Sebastian Palacio , Federico Raue , Andreas Dengel

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…

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…

计算机视觉与模式识别 · 计算机科学 2021-12-30 Xian Wei , Bin Wang , Mingsong Chen , Ji Yuan , Hai Lan , Jiehuang Shi , Xuan Tang , Bo Jin , Guozhang Chen , Dongping Yang

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Qihang Fan , Quanzeng You , Xiaotian Han , Yongfei Liu , Yunzhe Tao , Huaibo Huang , Ran He , Hongxia Yang

With the rapid development of computer vision, Vision Transformers (ViTs) offer the tantalising prospect of unified information processing across visual and textual domains due to the lack of inherent inductive biases in ViTs. ViTs require…

计算机视觉与模式识别 · 计算机科学 2025-08-25 Gousia Habib , Tausifa Jan Saleem , Ishfaq Ahmad Malik , Brejesh Lall

Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and…

计算机视觉与模式识别 · 计算机科学 2022-10-18 Shoufa Chen , Chongjian Ge , Zhan Tong , Jiangliu Wang , Yibing Song , Jue Wang , Ping Luo

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…

计算机视觉与模式识别 · 计算机科学 2023-05-23 Yanjing Li , Sheng Xu , Mingbao Lin , Xianbin Cao , Chuanjian Liu , Xiao Sun , Baochang Zhang

While vision transformers (ViTs) have shown great potential in computer vision tasks, their intense computation and memory requirements pose challenges for practical applications. Existing post-training quantization methods leverage value…

计算机视觉与模式识别 · 计算机科学 2024-02-02 Yu-Shan Tai , An-Yeu , Wu

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

机器学习 · 计算机科学 2025-12-24 Shoaib Mohammad , Guanqun Song , Ting Zhu

How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across all layers, extracted via sparse autoencoders, and by…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Jinyeong Kim , Junhyeok Kim , Yumin Shim , Joohyeok Kim , Sunyoung Jung , Seong Jae Hwang

In this work, we explore the quantization of diffusion models in extreme compression regimes to reduce model size while maintaining performance. We begin by investigating classical vector quantization but find that diffusion models are…

计算机视觉与模式识别 · 计算机科学 2024-11-20 Jie Shao , Hanxiao Zhang , Jianxin Wu

In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue this provides an insufficient representation and propose the…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Wenhao Li , Chengwei Ma , Weixin Mao

Assessing the forensic value of hand images involves the use of unique features and patterns present in an individual's hand. The human hand has distinct characteristics, such as the pattern of veins, fingerprints, and the geometry of the…

计算机视觉与模式识别 · 计算机科学 2024-08-21 Thanh Thi Nguyen , Campbell Wilson , Janis Dalins

Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to massive computational costs. Therefore, We propose a…

计算机视觉与模式识别 · 计算机科学 2022-11-22 Mengzhao Chen , Mingbao Lin , Ke Li , Yunhang Shen , Yongjian Wu , Fei Chao , Rongrong Ji