中文

Vision Transformers 是循环注意力学习者

计算机视觉与模式识别 2025-12-29 v1

摘要

自注意力机制一直是视觉 Transformer 取得进展的关键因素。然而,其二次复杂度在高分辨率场景下带来沉重的计算负担,限制了实际应用。先前方法通过引入局部性或稀疏性等手工模式来缓解此问题,却不可避免地损害模型容量。本文提出一种新颖注意力范式,称为循环注意力(Circulant Attention),通过利用自注意力的内在高效模式实现。具体而言,我们首先识别到视觉 Transformer 中的自注意力矩阵常常近似于具有循环子块的块循环矩阵(Block Circulant matrix with Circulant Blocks, BCCB),这是一种其矩阵乘法可在 O(NlogN)\mathcal{O}(N\log N) 时间内完成的结构矩阵。基于此有趣的模式,我们显式地将注意力图建模为其最近的 BCCB 矩阵,并提出一种高效计算算法进行快速计算。 resulting approach closely mirrors vanilla self-attention, differing only in its use of BCCB matrices. Since our design is inspired by the inherent efficient paradigm, it not only delivers O(NlogN)\mathcal{O}(N\log N) computation complexity, but also largely maintains the capacity of standard self-attention. Extensive experiments on diverse visual tasks demonstrate the effectiveness of our approach, establishing circulant attention as a promising alternative to self-attention for vision Transformer architectures. Code is available at https://github.com/LeapLabTHU/Circulant-Attention.

关键词

引用

@article{arxiv.2512.21542,
  title  = {Vision Transformers are Circulant Attention Learners},
  author = {Dongchen Han and Tianyu Li and Ziyi Wang and Gao Huang},
  journal= {arXiv preprint arXiv:2512.21542},
  year   = {2025}
}

备注

AAAI 2026