English

Couplformer:Rethinking Vision Transformer with Coupling Attention Map

Computer Vision and Pattern Recognition 2021-12-13 v1

Abstract

With the development of the self-attention mechanism, the Transformer model has demonstrated its outstanding performance in the computer vision domain. However, the massive computation brought from the full attention mechanism became a heavy burden for memory consumption. Sequentially, the limitation of memory reduces the possibility of improving the Transformer model. To remedy this problem, we propose a novel memory economy attention mechanism named Couplformer, which decouples the attention map into two sub-matrices and generates the alignment scores from spatial information. A series of different scale image classification tasks are applied to evaluate the effectiveness of our model. The result of experiments shows that on the ImageNet-1k classification task, the Couplformer can significantly decrease 28% memory consumption compared with regular Transformer while accessing sufficient accuracy requirements and outperforming 0.92% on Top-1 accuracy while occupying the same memory footprint. As a result, the Couplformer can serve as an efficient backbone in visual tasks, and provide a novel perspective on the attention mechanism for researchers.

Keywords

Cite

@article{arxiv.2112.05425,
  title  = {Couplformer:Rethinking Vision Transformer with Coupling Attention Map},
  author = {Hai Lan and Xihao Wang and Xian Wei},
  journal= {arXiv preprint arXiv:2112.05425},
  year   = {2021}
}

Comments

11 pages, 4 figures

R2 v1 2026-06-24T08:12:00.281Z