Transformers in Vision: A Survey. (arXiv:2101.01169v5 [cs.CV] UPDATED)

Astounding results from Transformer models on natural language tasks have
intrigued the vision community to study their application to computer vision
problems. Among their salient benefits, Transformers enable modeling long
dependencies between input sequence elements and support parallel processing of
sequence as compared to recurrent networks e.g., Long short-term memory (LSTM).
Different from convolutional networks, Transformers require minimal inductive
biases for their design and are naturally suited as set-functions. Furthermore,
the straightforward design of Transformers allows processing multiple
modalities (e.g., …

arxiv cv survey transformers vision