Token Pruning Meets Audio: Investigating Unique Behaviors in Vision Transformer-Based Audio Classification
Keywords: Audio Spectrogram Transformer, Token Pruning
TL;DR: Token pruning in ViT for audio classification retains both low-intensity background tokens and high-intensity signal tokens and both of them contribute to classification accuracy.
Abstract: This submission is withdrawn due to errors in our token pruning analysis, which led to inaccurate claims regarding the retention of signal versus background tokens in AudioMAE-TopK. We have withdrawn our paper to prevent researchers from directly downloading it via the permanent hyperlink on OpenReview and relying on flawed information for their experiments. Please refer to the withdrawal statement for details.
We are truly sorry for any inconvenience our error has caused.
Primary Area: other topics in machine learning (i.e., none of the above)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 9332
Loading