English
Related papers

Related papers: An Attention Free Transformer

200 papers

Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Chengxing Xie , Xiaoming Zhang , Linze Li , Yuqian Fu , Biao Gong , Tianrui Li , Kai Zhang

The Transformer architecture has two main non-embedding components: Attention and the Feed Forward Network (FFN). Attention captures interdependencies between words regardless of their position, while the FFN non-linearly transforms each…

Computation and Language · Computer Science 2023-10-24 Telmo Pessoa Pires , António V. Lopes , Yannick Assogba , Hendra Setiawan

Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the success is limited to small-scale graphs due to the drawbacks of…

Machine Learning · Computer Science 2022-10-05 Jinyoung Park , Seongjun Yun , Hyeonjin Park , Jaewoo Kang , Jisu Jeong , Kyung-Min Kim , Jung-woo Ha , Hyunwoo J. Kim

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, which becomes infeasible…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 John Guibas , Morteza Mardani , Zongyi Li , Andrew Tao , Anima Anandkumar , Bryan Catanzaro

Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…

Machine Learning · Computer Science 2023-07-24 Hengyu Fu , Tianyu Guo , Yu Bai , Song Mei

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Hwanjun Song , Deqing Sun , Sanghyuk Chun , Varun Jampani , Dongyoon Han , Byeongho Heo , Wonjae Kim , Ming-Hsuan Yang

In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Wele Gedara Chaminda Bandara , Vishal M. Patel

Recently Transformer has shown good performance in several vision tasks due to its powerful modeling capabilities. To reduce the quadratic complexity caused by the attention, some outstanding work restricts attention to local regions or…

Computer Vision and Pattern Recognition · Computer Science 2023-05-03 Fangjian Lin , Yizhe Ma , Sitong Wu , Long Yu , Shengwei Tian

Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, are often considerably more complex than image…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Ryota Yoshihashi , Masahiro Kada , Satoshi Ikehata , Rei Kawakami , Ikuro Sato

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Computation and Language · Computer Science 2025-09-19 Yanming Kang , Giang Tran , Hans De Sterck

Though image transformers have shown competitive results with convolutional neural networks in computer vision tasks, lacking inductive biases such as locality still poses problems in terms of model efficiency especially for embedded…

Computer Vision and Pattern Recognition · Computer Science 2022-07-08 Ling Li , Ali Shafiee Ardestani , Joseph Hassoun

Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value…

Machine Learning · Computer Science 2025-12-30 Xiaowei Wang

Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with…

Machine Learning · Computer Science 2025-02-14 Edoardo Cetin , Qi Sun , Tianyu Zhao , Yujin Tang

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Computation and Language · Computer Science 2025-11-20 Xiuying Wei , Anunay Yadav , Razvan Pascanu , Caglar Gulcehre

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Sucheng Ren , Daquan Zhou , Shengfeng He , Jiashi Feng , Xinchao Wang

Self-attention networks (SANs) have drawn increasing interest due to their high parallelization in computation and flexibility in modeling dependencies. SANs can be further enhanced with multi-head attention by allowing the model to attend…

Computation and Language · Computer Science 2019-04-08 Baosong Yang , Longyue Wang , Derek Wong , Lidia S. Chao , Zhaopeng Tu

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-29 Shucong Zhang , Erfan Loweimi , Peter Bell , Steve Renals

Recent works have demonstrated that transformer can achieve promising performance in computer vision, by exploiting the relationship among image patches with self-attention. While they only consider the attention in a single feature layer,…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Nannan Li , Yaran Chen , Weifan Li , Zixiang Ding , Dongbin Zhao

We propose FMMformers, a class of efficient and flexible transformers inspired by the celebrated fast multipole method (FMM) for accelerating interacting particle simulation. FMM decomposes particle-particle interaction into near-field and…

Machine Learning · Computer Science 2021-08-06 Tan M. Nguyen , Vai Suliafu , Stanley J. Osher , Long Chen , Bao Wang