Are we ready for a new paradigm shift? A Survey on Visual Deep MLP
This is an incremental review paper for the computer vision community, analyzing the potential of MLPs as a paradigm shift.
This survey examines whether deep MLP models can become a new paradigm in computer vision, comparing them to convolution and self-attention mechanisms, and suggests aligning future developments with next-generation computing devices.
Recently, the proposed deep MLP models have stirred up a lot of interest in the vision community. Historically, the availability of larger datasets combined with increased computing capacity leads to paradigm shifts. This review paper provides detailed discussions on whether MLP can be a new paradigm for computer vision. We compare the intrinsic connections and differences between convolution, self-attention mechanism, and Token-mixing MLP in detail. Advantages and limitations of Token-mixing MLP are provided, followed by careful analysis of recent MLP-like variants, from module design to network architecture, and their applications. In the GPU era, the locally and globally weighted summations are the current mainstreams, represented by the convolution and self-attention mechanism, as well as MLP. We suggest the further development of paradigm to be considered alongside the next-generation computing devices.