paper-with-me

Papers

An Investigation into Whitening Loss for Self-supervised Learning

2022-10-07 · Xi Weng, Lei Huang, Lei Zhao, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan

A desirable objective in self-supervised learning (SSL) is to avoid feature collapse. Whitening loss guarantees collapse avoidance by minimizing the distance between embeddings of positive pairs under the conditioning that the embeddings from different views are whitened. In this paper, we propose a framework with an informative indicator to analyze whitening loss, which provides a clue to demystify several interesting phenomena as well as a pivoting point connecting to other SSL methods. We reveal that batch whitening (BW) based methods do not impose whitening constraints on the embedding, but they only require the embedding to be full-rank. This full-rank constraint is also sufficient to avoid dimensional collapse. Based on our analysis, we propose channel whitening with random group partition (CW-RGP), which exploits the advantages of BW-based methods in preventing collapse and avoids their disadvantages requiring large batch size. Experimental results on ImageNet classification and COCO object detection reveal that the proposed CW-RGP possesses a promising potential for learning good representations. The code is available at https://github.com/winci-ai/CW-RGP.

📄 PDF Abstract BibTeX arXiv:2210.03586

Code (1)

winci-ai/cw-rgp 공식 구현 pytorch

Tasks

object-detectionObject DetectionSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Modulate Your Spectrum in Self-Supervised Learning

2023-05-26 · Xi Weng, Yunhao Ni, Tengwei Song, Jie Luo 외

Whitening loss offers a theoretical guarantee against feature collapse in self-supervised learning (SSL) with joint embedding architectures. Typically, it involves a hard whitening approach, transforming the embedding an…

object-detectionObject DetectionSelf-Supervised Learning

Whitening for Self-Supervised Representation Learning

2020-07-13 · Aleksandr Ermolov, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe

Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are cont…

Representation LearningSelf-Supervised Learning

Whitening Consistently Improves Self-Supervised Learning

2024-08-14 · András Kalapos, Bálint Gyires-Tóth

Self-supervised learning (SSL) has been shown to be a powerful approach for learning visual representations. In this study, we propose incorporating ZCA whitening as the final layer of the encoder in self-supervised lear…

Self-Supervised Learning

GUESS: Generative Uncertainty Ensemble for Self Supervision

2024-12-03 · Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh

Self-supervised learning (SSL) frameworks consist of pretext task, and loss function aiming to learn useful general features from unlabeled data. The basic idea of most SSL baselines revolves around enforcing the invaria…

Data AugmentationSelf-Supervised Learning

Metric-Aware Principal Component Analysis (MAPCA):A Unified Framework for Scale-Invariant Representation Learning

2026-04-15 · Michael Leznik arxiv

We introduce Metric-Aware Principal Component Analysis (MAPCA), a unified framework for scale-invariant representation learning based on the generalised eigenproblem max Tr(W^T Sigma W) subject to W^T M W = I, where M is…

Self-Supervised LearningRepresentation Learning