paper-with-me

홈 › Papers

Understanding the Role of Equivariance in Self-supervised Learning

2024-11-10 · Yifei Wang, Kaiwen Hu, Sharut Gupta, Ziyu Ye, Yisen Wang, Stefanie Jegelka

Contrastive learning has been a leading paradigm for self-supervised learning, but it is widely observed that it comes at the price of sacrificing useful features (\eg colors) by being invariant to data augmentations. Given this limitation, there has been a surge of interest in equivariant self-supervised learning (E-SSL) that learns features to be augmentation-aware. However, even for the simplest rotation prediction method, there is a lack of rigorous understanding of why, when, and how E-SSL learns useful features for downstream tasks. To bridge this gap between practice and theory, we establish an information-theoretic perspective to understand the generalization ability of E-SSL. In particular, we identify a critical explaining-away effect in E-SSL that creates a synergy between the equivariant and classification tasks. This synergy effect encourages models to extract class-relevant features to improve its equivariant prediction, which, in turn, benefits downstream tasks requiring semantic features. Based on this perspective, we theoretically analyze the influence of data transformations and reveal several principles for practical designs of E-SSL. Our theory not only aligns well with existing E-SSL methods but also sheds light on new directions by exploring the benefits of model equivariance. We believe that a theoretically grounded understanding on the role of equivariance would inspire more principled and advanced designs in this field. Code is available at https://github.com/kaotty/Understanding-ESSL.

📄 PDF Abstract BibTeX arXiv:2411.06508

Code (1)

kaotty/understanding-essl 공식 구현 pytorch

Tasks

Contrastive LearningSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Equivariance-based self-supervised learning for audio signal recovery from clipped measurements

2024-09-03 · Victor Sechaud, Laurent Jacques, Patrice Abry, Julián Tachella

<div><p>In numerous inverse problems, state-of-the-art solving strategies involve training neural networks from ground truth and associated measurement datasets that, however, may be expensive or impossible to collect. R…

Self-Supervised Learning

Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation

2022-06-26 · Jinxiang Liu, Chen Ju, Weidi Xie, Ya zhang

We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos. To understand what enables to learn useful representations, we systematically …

Cross-Modal RetrievalRepresentation LearningRetrieval

MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music

2026-07-16 · Scott H. Hawley arxiv

Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplo…

Representation LearningEmotion Classification

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

2021-09-29 · ICLR 2022 4 · Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han 외

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, th…

Self-Supervised Learning

PooDLe: Pooled and dense self-supervised learning from naturalistic videos

2024-08-20 · Alex N. Wang, Christopher Hoang, Yuwen Xiong, Yann Lecun 외

Self-supervised learning has driven significant progress in learning from single-subject, iconic images. However, there are still unanswered questions about the use of minimally-curated, naturalistic video data, which co…

Optical Flow EstimationSelf-Supervised Learning