Token Merging: Your ViT But Faster
Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, Judy Hoffman
Abstract
We introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a transformer using a general and light-weight matching algorithm that is as fast as pruning while being more accurate. Off-the-shelf, ToMe can 2x the throughput of state-of-the-art ViT-L @ 512 and ViT-H @ 518 models on images and 2.2x the throughput of ViT-L on video with only a 0.2-0.3% accuracy drop in each case. ToMe can also easily be applied during training, improving in practice training speed up to 2x for MAE fine-tuning on video. Training with ToMe further minimizes accuracy drop, leading to 2x the throughput of ViT-B on audio for only a 0.4% mAP drop. Qualitatively, we find that ToMe merges object parts into one token, even over multiple frames of video. Overall, ToMe’s accuracy and speed are competitive with state-of-the-art on images, video, and audio.
BibTeX
@inproceedings{
bolya2023token,
title={Token Merging: Your ViT But Faster},
author={Daniel Bolya and Cheng-Yang Fu and Xiaoliang Dai and Peizhao Zhang and Christoph Feichtenhofer and Judy Hoffman},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=JroZRaRw7Eu}
}