Papers
arxiv:2409.11923

Agglomerative Token Clustering

Published on Sep 18, 2024
Authors:
,
,

Abstract

We present Agglomerative Token Clustering (ATC), a novel token merging method that consistently outperforms previous token merging and pruning methods across image classification, image synthesis, and object detection & segmentation tasks. ATC merges clusters through bottom-up hierarchical clustering, without the introduction of extra learnable parameters. We find that ATC achieves state-of-the-art performance across all tasks, and can even perform on par with prior state-of-the-art when applied off-the-shelf, i.e. without fine-tuning. ATC is particularly effective when applied with low keep rates, where only a small fraction of tokens are kept and retaining task performance is especially difficult.

Community

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment

Models citing this paper 45

Browse 45 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2409.11923 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2409.11923 in a Space README.md to link it from this page.

Collections including this paper 1