S2-MLPv2: Improved Spatial-Shift MLP Architecture for Vision

Recently, MLP-based vision backbones emerge. MLP-based vision architectures with less inductive bias achieve competitive performance in image recognition compared with CNNs and vision Transformers. Among them, spatial-shift MLP (S-MLP), adopting the straightforward spatial-shift operation, achieves better performance than the pioneering works including MLP-mixer and ResMLP. More recently, using smaller patches with a pyramid structure, Vision Permutator (ViP) and Global Filter Network (GFNet) achieve better performance than S-MLP. In this paper, we improve the S-MLP vision backbone. We expand the feature map along the channel dimension and split the expanded feature map into several parts. We conduct different spatial-shift operations on split parts. Meanwhile, we exploit the split-attention operation to fuse these split parts. Moreover, like the counterparts, we adopt smaller-scale patches and use a pyramid structure for boosting the image recognition accuracy. We term the improved spatial-shift MLP vision backbone as S-MLPv2. Using 55M parameters, our medium-scale model, SMLPv2-Medium achieves an 83.6% top-1 accuracy on the ImageNet-1K benchmark using 224× 224 images without self-attention and external training data.