Saved in:
Bibliographic Details
Main Authors: Fang, Xianghong, Li, Jian, Sun, Qiang, Wang, Benyou
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.00642
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913329705910272
author Fang, Xianghong
Li, Jian
Sun, Qiang
Wang, Benyou
author_facet Fang, Xianghong
Li, Jian
Sun, Qiang
Wang, Benyou
contents Uniformity plays an important role in evaluating learned representations, providing insights into self-supervised learning. In our quest for effective uniformity metrics, we pinpoint four principled properties that such metrics should possess. Namely, an effective uniformity metric should remain invariant to instance permutations and sample replications while accurately capturing feature redundancy and dimensional collapse. Surprisingly, we find that the uniformity metric proposed by \citet{Wang2020UnderstandingCR} fails to satisfy the majority of these properties. Specifically, their metric is sensitive to sample replications, and can not account for feature redundancy and dimensional collapse correctly. To overcome these limitations, we introduce a new uniformity metric based on the Wasserstein distance, which satisfies all the aforementioned properties. Integrating this new metric in existing self-supervised learning methods effectively mitigates dimensional collapse and consistently improves their performance on downstream tasks involving CIFAR-10 and CIFAR-100 datasets. Code is available at \url{https://github.com/statsle/WassersteinSSL}.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00642
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rethinking The Uniformity Metric in Self-Supervised Learning
Fang, Xianghong
Li, Jian
Sun, Qiang
Wang, Benyou
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Uniformity plays an important role in evaluating learned representations, providing insights into self-supervised learning. In our quest for effective uniformity metrics, we pinpoint four principled properties that such metrics should possess. Namely, an effective uniformity metric should remain invariant to instance permutations and sample replications while accurately capturing feature redundancy and dimensional collapse. Surprisingly, we find that the uniformity metric proposed by \citet{Wang2020UnderstandingCR} fails to satisfy the majority of these properties. Specifically, their metric is sensitive to sample replications, and can not account for feature redundancy and dimensional collapse correctly. To overcome these limitations, we introduce a new uniformity metric based on the Wasserstein distance, which satisfies all the aforementioned properties. Integrating this new metric in existing self-supervised learning methods effectively mitigates dimensional collapse and consistently improves their performance on downstream tasks involving CIFAR-10 and CIFAR-100 datasets. Code is available at \url{https://github.com/statsle/WassersteinSSL}.
title Rethinking The Uniformity Metric in Self-Supervised Learning
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.00642