pith. sign in

arxiv: 2112.05425 · v1 · pith:3UGXX4TInew · submitted 2021-12-10 · 💻 cs.CV

Couplformer:Rethinking Vision Transformer with Coupling Attention Map

classification 💻 cs.CV
keywords attentionmemorycouplformermechanismtransformermodelaccuracyclassification
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.