Token Merging (ToMe) doubles the throughput of large Vision Transformers on images, video, and audio by merging similar tokens with a fast matching algorithm, incurring only 0.2-0.4% accuracy loss.
A.2 V IDEO We run the ViT-L model from Feichtenhofer et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Token Merging: Your ViT But Faster
Token Merging (ToMe) doubles the throughput of large Vision Transformers on images, video, and audio by merging similar tokens with a fast matching algorithm, incurring only 0.2-0.4% accuracy loss.