Log In Sign Up

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

by   Adrien Bardes, et al.

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.


page 1

page 2

page 3

page 4


TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning

We present Transformation Invariance and Covariance Contrast (TiCo) for ...

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations

Self-Supervised Learning (SSL) methods such as VICReg, Barlow Twins or W...

VIbCReg: Variance-Invariance-better-Covariance Regularization for Self-Supervised Learning on Time Series

Self-supervised learning for image representations has recently had many...

EquiMod: An Equivariance Module to Improve Self-Supervised Learning

Self-supervised visual representation methods are closing the gap with s...

Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head

One unexpected technique that emerged in recent years consists in traini...

Side-Informed Steganography for JPEG Images by Modeling Decompressed Images

Side-informed steganography has always been among the most secure approa...

Self-Supervised Representation Learning With MUlti-Segmental Informational Coding (MUSIC)

Self-supervised representation learning maps high-dimensional data into ...