English
Related papers

Related papers: Flash Window Attention: speedup the attention comp…

200 papers

Vision Transformers achieved outstanding performance in many computer vision tasks. Early Vision Transformers such as ViT and DeiT adopt global self-attention, which is computationally expensive when the number of patches is large. To…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Tan Yu , Gangming Zhao , Ping Li , Yizhou Yu

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Machine Learning · Computer Science 2024-01-22 Yang Li , Liangzhen Lai , Yuan Shangguan , Forrest N. Iandola , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

Computation and Language · Computer Science 2025-06-05 Zichuan Fu , Wentao Song , Yejing Wang , Xian Wu , Yefeng Zheng , Yingying Zhang , Derong Xu , Xuetao Wei , Tong Xu , Xiangyu Zhao

The Swin transformer has recently attracted attention in medical image analysis due to its computational efficiency and long-range modeling capability. Owing to these properties, the Swin Transformer is suitable for establishing more…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Mingrui Ma , Tao Wang , Lei Song , Weijie Wang , Guixia Liu

In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to non overlapping…

Image and Video Processing · Electrical Eng. & Systems 2024-12-11 Song-Jiang Lai , Tsun-Hin Cheung , Ka-Chun Fung , Kai-wen Xue , Kin-Man Lam

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Jianwei Yang , Chunyuan Li , Pengchuan Zhang , Xiyang Dai , Bin Xiao , Lu Yuan , Jianfeng Gao

Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Zilong Huang , Youcheng Ben , Guozhong Luo , Pei Cheng , Gang Yu , Bin Fu

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Machine Learning · Computer Science 2025-11-25 Jeffrey Willette , Heejun Lee , Sung Ju Hwang

Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Zhuoran Shen , Mingyuan Zhang , Haiyu Zhao , Shuai Yi , Hongsheng Li

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…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Puskal Khadka , Rodrigue Rizk , Longwei Wang , KC Santosh

While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Daniel Bolya , Cheng-Yang Fu , Xiaoliang Dai , Peizhao Zhang , Judy Hoffman

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

The quadratic time and memory complexity of the attention mechanism in modern Transformer based video generators makes end-to-end training for ultra high resolution videos prohibitively expensive. Motivated by this limitation, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Yunfeng Wu , Jiayi Song , Zhenxiong Tan , Zihao He , Songhua Liu

The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of $O(N^2)$, compared to $O(N)$ for linear transformations. When handling large sequence lengths,…

Machine Learning · Computer Science 2025-10-02 Jintao Zhang , Jia Wei , Haofeng Huang , Pengle Zhang , Jun Zhu , Jianfei Chen

Transformer-based models have revolutionized the field of image super-resolution (SR) by harnessing their inherent ability to capture complex contextual features. The overlapping rectangular shifted window technique used in transformer…

Image and Video Processing · Electrical Eng. & Systems 2024-03-26 Abhisek Ray , Gaurav Kumar , Maheshkumar H. Kolekar

The attention mechanism is the key to the success of transformers in different machine learning tasks. However, the quadratic complexity with respect to the sequence length of the vanilla softmax-based attention mechanism becomes the major…

Image and Video Processing · Electrical Eng. & Systems 2025-08-05 Chong Wu , Maolin Che , Renjie Xu , Zhuoheng Ran , Hong Yan

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…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Chaodong Xiao , Zhengqiang Zhang , Lei Zhang

With the popularity of Transformer architectures in computer vision, the research focus has shifted towards developing computationally efficient designs. Window-based local attention is one of the major techniques being adopted in recent…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Ammarah Farooq , Muhammad Awais , Sara Ahmed , Josef Kittler

Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs). Despite…

Image and Video Processing · Electrical Eng. & Systems 2022-04-12 Renjie Zou , Chunfeng Song , Zhaoxiang Zhang

Despite the tantalizing success in a broad of vision tasks, transformers have not yet demonstrated on-par ability as ConvNets in high-resolution image generative modeling. In this paper, we seek to explore using pure transformers to build a…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Bowen Zhang , Shuyang Gu , Bo Zhang , Jianmin Bao , Dong Chen , Fang Wen , Yong Wang , Baining Guo