Are we ready for a new paradigm shift? A Survey on Visual Deep MLP

Multilayer perceptron (MLP), as the first neural network structure to appear, was a big hit. But constrained by the hardware computing power and the size of the datasets, it once sank for tens of years. During this period, we have witnessed a paradigm shift from manual feature extraction to the CNN with local receptive fields, and further to the Transform with global receptive fields based on self-attention mechanism. And this year (2021), with the introduction of MLP-Mixer, MLP has re-entered the limelight and has attracted extensive research from the computer vision community. Compare to the conventional MLP, it gets deeper but changes the input from full flattening to patch flattening. Given its high performance and less need for vision-specific inductive bias, the community can't help but wonder, Will MLP, the simplest structure with global receptive fields but no attention, become a new computer vision paradigm? To answer this question, this survey aims to provide a comprehensive overview of the recent development of vision deep MLP models. Specifically, we review these vision deep MLPs detailedly, from the subtle sub-module design to the global network structure. We compare the receptive field, computational complexity, and other properties of different network designs in order to have a clear understanding of the development path of MLPs. The investigation shows that MLPs' resolution-sensitivity and computational densities remain unresolved, and pure MLPs are gradually evolving towards CNN-like. We suggest that the current data volume and computational power are not ready to embrace pure MLPs, and artificial visual guidance remains important. Finally, we provide an analysis of open research directions and possible future works. We hope this effort will ignite further interest in the community and encourage better visual tailored design for the neural network at the moment.