Keep It SimPool:Who Said Supervised Transformers Suffer from Attention Deficit?
Work
Year: 2023
Type: article
Abstract: Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? ... more
Institution National Technical University of Athens
Cites: 53
Cited by: 6
Related to: 10
FWCI: 1.397
Citation percentile (by year/subfield): 100
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green