A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformers. (arXiv:2206.11073v1 [cs.NE])

Vision transformer (ViT) and its variants have achieved remarkable successes
in various visual tasks. The key characteristic of these ViT models is to adopt
different aggregation strategies of spatial patch information within the
artificial neural networks (ANNs). However, there is still a key lack of
unified representation of different ViT architectures for systematic
understanding and assessment of model representation performance. Moreover, how
those well-performing ViT ANNs are similar to real biological neural networks
(BNNs) is largely unexplored. To answer these …

arxiv graph graph representation representation transformers vision