ResT V2: Simpler, Faster and Stronger

This paper proposes ResTv2, a simpler, faster, and stronger multi-scale vision Transformer for visual recognition. ResTv2 simplifies the EMSA structure in ResTv1 (i.e., eliminating the multi-head interaction part) and employs an upsample operation to reconstruct the lost medium-and high-frequency information caused by the downsampling operation. In addition, we explore different techniques for better applying ResTv2 backbones to downstream tasks. We find that although combining EMSAv2 and window attention can greatly reduce the theoretical matrix multiply FLOPs, it may significantly decrease the computation density, thus causing lower actual speed.