Efficient ViTs

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

Papers

Showing 31–32 of 32 papers

Title	Date	Tasks	Status	Hype
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers	Nov 21, 2022	Computational EfficiencyDiversity	CodeCode Available	0
Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer	May 6, 2024	Efficient ViTsModel Compression	CodeCode Available	0

Show:10 25 50

← PrevPage 4 of 4Next →

No leaderboard results yet.