Comparative Analysis between Vision Transformers and CNNs from the view of Neuroscience

Xiuyuan Hu, Hao Zhang, Yang Zhao

Keywords: Vision Transformer, CNN, neuroscience, sparsity

Abstract: Neuroscience has provide many inspirations for the development of artificial intelligence, especially for neural networks for computer vision tasks. Recent research on animals' visual systems builds the connection between neural sparsity and animals' levels of evolution, based on which comparisons between two most influential vision architecture, Transformer and CNN, are carried out. In particular, the sparsity of attentions in Transformers is comprehensively studied, and previous knowledge on sparsity of neurons in CNNs is reviewed. In addition, a novel metric for neural sparsity is defined and ablation experiments are launched on various types of Transformer and CNN models. Finally, we draw the conclusion that more layers in models will result in higher sparsity, however, too many heads in Transformers may cause reduction of sparsity, which attributes to the significant overlap among effects of attention units.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)

TL;DR: Neural sparsity of Transformers and CNNs are defined and calculated, leading to striking conclusion.