OpenGVLab / DiffRateLinks
[ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.
☆99Updated 2 years ago
Alternatives and similar repositories for DiffRate
Users that are interested in DiffRate are comparing it to the libraries listed below
Sorting:
- Official implementation for paper "Knowledge Diffusion for Distillation", NeurIPS 2023☆88Updated last year
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆34Updated last year