English
Related papers

Related papers: SHViT: Single-Head Vision Transformer with Memory …

200 papers

Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention…

Hardware Architecture · Computer Science 2023-09-14 Rishov Sarkar , Hanxue Liang , Zhiwen Fan , Zhangyang Wang , Cong Hao

Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Huanjin Yao , Wenhao Wu , Zhiheng Li

Humans see low spatial frequency components before high spatial frequency components. Drawing on this neuroscientific inspiration, we investigate the effect of introducing patches from different spatial frequencies into Vision Transformers…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Yuyang Shu , Michael E. Bain

As emerging hardware begins to support mixed bit-width arithmetic computation, mixed-precision quantization is widely used to reduce the complexity of neural networks. However, Vision Transformers (ViTs) require complex self-attention…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Junrui Xiao , Zhikai Li , Lianwei Yang , Qingyi Gu

This paper presents the Sensorimotor Transformer (SMT), a vision model inspired by human saccadic eye movements that prioritize high-saliency regions in visual input to enhance computational efficiency and reduce memory consumption. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Konrad Gadzicki , Kerstin Schill , Christoph Zetzsche

Transformers have astounding representational power but typically consume considerable computation which is quadratic with image resolution. The prevailing Swin transformer reduces computational costs through a local window strategy.…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Haolin Qin , Daquan Zhou , Tingfa Xu , Ziyang Bian , Jianan Li

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…

Computer Vision and Pattern Recognition · Computer Science 2024-12-04 Jinqi Xiao , Miao Yin , Yu Gong , Xiao Zang , Jian Ren , Bo Yuan

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

Computation and Language · Computer Science 2023-05-31 Arash Ardakani , Altan Haan , Shangyin Tan , Doru Thom Popovici , Alvin Cheung , Costin Iancu , Koushik Sen

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Hongxu Yin , Arash Vahdat , Jose Alvarez , Arun Mallya , Jan Kautz , Pavlo Molchanov

Vision Transformers has demonstrated competitive performance on computer vision tasks benefiting from their ability to capture long-range dependencies with multi-head self-attention modules and multi-layer perceptron. However, calculating…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xiangyu Chen , Qinghao Hu , Kaidong Li , Cuncong Zhong , Guanghui Wang

Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Hwanjun Song , Deqing Sun , Sanghyuk Chun , Varun Jampani , Dongyoon Han , Byeongho Heo , Wonjae Kim , Ming-Hsuan Yang

As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Sanchit Sinha , Guangzhi Xiong , Aidong Zhang

For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs' output remains sensitive to small spatial shifts in the input, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Renan A. Rojas-Gomez , Teck-Yian Lim , Minh N. Do , Raymond A. Yeh

Vision Transformers (ViTs) have established new performance benchmarks in vision tasks such as image recognition and object detection. However, these advancements come with significant demands for memory and computational resources,…

Hardware Architecture · Computer Science 2026-02-10 Cong Wang , Zexin Fu , Jiayi Huang , Shanshi Huang

Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video processing. Although there have been efforts to improve the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Jing Zhang , Zhikai Li , Xuewen Liu , Qingyi Gu

The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Ting Yao , Yehao Li , Yingwei Pan , Tao Mei

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…

Computer Vision and Pattern Recognition · Computer Science 2023-02-09 Jiayu Jiao , Yu-Ming Tang , Kun-Yu Lin , Yipeng Gao , Jinhua Ma , Yaowei Wang , Wei-Shi Zheng

Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens. However, the high computational and memory demands of ViTs pose…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Zhengqing Yuan , Rong Zhou , Hongyi Wang , Lifang He , Yanfang Ye , Lichao Sun

Recently, Transformers have shown promising performance in various vision tasks. However, the high costs of global self-attention remain challenging for Transformers, especially for high-resolution vision tasks. Inspired by one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Zhemin Zhang , Xun Gong

We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Ali Hatamizadeh , Hongxu Yin , Greg Heinrich , Jan Kautz , Pavlo Molchanov