paper-with-me

Papers

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

2021-05-11 · NeurIPS 2021 12 · Adrien Bardes, Jean Ponce, Yann Lecun

Recent self-supervised methods for image representation learning are based on maximizing the agreement between embedding vectors from different views of the same image. A trivial solution is obtained when the encoder outputs constant vectors. This collapse problem is often avoided through implicit biases in the learning architecture, that often lack a clear justification or interpretation. In this paper, we introduce VICReg (Variance-Invariance-Covariance Regularization), a method that explicitly avoids the collapse problem with a simple regularization term on the variance of the embeddings along each dimension individually. VICReg combines the variance term with a decorrelation mechanism based on redundancy reduction and covariance regularization, and achieves results on par with the state of the art on several downstream tasks. In addition, we show that incorporating our new variance term into other methods helps stabilize the training and leads to performance improvements.

📄 PDF Abstract BibTeX arXiv:2105.04906

Code (6)

facebookresearch/vicreg 공식 구현 pytorch
AnnaManasyan/VICReg pytorch
FloCF/SSL_pytorch pytorch
lightly-ai/lightly pytorch
vturrisi/solo-learn pytorch
https://gitlab.com/birder/birder pytorch

Tasks

Representation LearningSelf-Supervised Image ClassificationSelf-Supervised LearningSemi-Supervised Image Classification

Similar Papers 제목 키워드 기반

An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization

2023-03-01 · Ravid Shwartz-Ziv, Randall Balestriero, Kenji Kawaguchi, Tim G. J. Rudner 외

Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised learning (SSL) method that has shown promising results on a variety of tasks. However, the fundamental mechanisms underlying VICReg remain unexp…

Self-Supervised LearningTransfer Learning

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

2023-09-21 · NeurIPS 2023 11

Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised learning (SSL) method that has shown promising results on a variety of tasks. However, the fundamental mechanisms underlying VICReg remain unexp…

VISReg: Variance-Invariance-Sketching Regularization for JEPA training

2026-06-01 · Haiyu Wu, Randall Balestriero, Morgan Levine arxiv

Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regularization into variance and covariance objec…

Self-Supervised Learning

VNIbCReg: VICReg with Neighboring-Invariance and better-Covariance Evaluated on Non-stationary Seismic Signal Time Series

2022-04-06 · Daesoo Lee, Erlend Aune, Nadège Langet, Jo Eidsvik

One of the latest self-supervised learning (SSL) methods, VICReg, showed a great performance both in the linear evaluation and the fine-tuning evaluation. However, VICReg is proposed in computer vision and it learns by p…

Linear evaluationSelf-Supervised LearningTime SeriesTime Series Analysis

Self-Supervised Learning Based Handwriting Verification

2024-05-28 · Mihir Chauhan, Mohammad Abuzar Shaikh, Bina Ramamurthy, Mingchen Gao 외

We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different write…

Handwriting VerificationSelf-Supervised Learning