SOTAVerified

Efficient ViTs

Increasing the efficiency of ViTs without the modification of the architecture. (i.e., Key & Query Sparsification, Token pruning & merging)

Papers

Showing 3132 of 32 papers

TitleStatusHype
Scalable Vision Transformers with Hierarchical PoolingCode1
Training data-efficient image transformers & distillation through attentionCode1
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.