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

arxiv:2105.04906

Original source · Paper JSON

Self-supervised learning and vision · 2021-05-11

Cites (1) · Cited by (6)

Complete cleaned Markdown · Source Markdown including bibliography

Read in parts

1. Part 1
2. Part 2
3. Part 3

Contents

• VICReg: Variance-Invariance-Covariance Re-gularization for Self-Supervised Learning
• Abstract
• 1 Introduction
• 2 VICReg: intuition
• 3 Related work
• 4 VICReg: detailed description
• 4.1 Method
• 4.2 Implementation details
• 5 Results
• 5.1 Evaluation on ImageNet
• 5.2 Transfer to other downstream tasks
• 5.3 Multi-modal pretraining on MS-COCO
• 6 Analysis
• 7 Conclusion