OpenGVLab/DiffRate

[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.

by OpenGVLab Jupyter Notebook 7 forks Created May 2023 View on GitHub

Stars: 103; <1% of OpenGVLab's stars
Rank: #475,347; of 852,369 repos, top 56%
In Jupyter Notebook: #11,157; of 21,669 repos, top 52%

Among 852,369 repos

All repos Jupyter Notebook

100–160 stars: 155,646 repos, including DiffRate

top 50%top 10%top 1%top 0.1%

Stars along the bottom, and repos in each band on a log scale

Quick stats

Next rank: +1 star to reach #471,683
Next milestone: +16 stars to reach the top 50%
Popular: One of 490,939 repos with 100+ stars
Yearly average: 30 stars a year since May 2023