SpiralMLP: A Lightweight Vision MLP Architecture

arXiv:2404.00648v1 Announce Type: new
Abstract: We present SpiralMLP, a novel architecture that introduces a Spiral FC layer as a replacement for the conventional Token Mixing approach. Differing from several existing MLP-based models that primarily emphasize axes, our Spiral FC layer is designed as a deformable convolution layer with spiral-like offsets. We further adapt Spiral FC into two variants: Self-Spiral FC and Cross-Spiral FC, which enable both local and global feature integration seamlessly, eliminating the need for additional processing steps. To …

abstract adapt architecture arxiv convolution cs.cv layer mlp novel replacement token type vision