ConvFormer: Closing the Gap Between CNN and Vision Transformers. (arXiv:2209.07738v1 [cs.CV] CROSS LISTED)

Vision transformers have shown excellent performance in computer vision
tasks. However, the computation cost of their (local) self-attention mechanism
is expensive. Comparatively, CNN is more efficient with built-in inductive
bias. Recent works show that CNN is promising to compete with vision
transformers by learning their architecture design and training protocols.
Nevertheless, existing methods either ignore multi-level features or lack
dynamic prosperity, leading to sub-optimal performance. In this paper, we
propose a novel attention mechanism named MCA, which captures different
patterns …

arxiv cnn gap transformers vision