On the Role of the Projector in Contrastive Self-Supervised Learning: Last-Layer Rank Dynamics Drive Representation Quality

arXiv:2609.26334 · cs.CV · Submitted 2026-09-22 · Read on arXiv

cs.CV

Submitted: 2026-09-22

Updated: 2026-09-22

Code: https://github.com/lightly-ai/lightly

Terminology

• Regularization — 36× in this paper · explained in 3 episodes
• Embeddings — 32× in this paper · explained in 2 episodes
• Self-Supervised Learning — 17× in this paper · explained in 8 episodes
• Contrastive Learning — 14× in this paper · explained in 5 episodes
• Representation Learning — 10× in this paper · explained in 2 episodes
• Barlow Twins — 8× in this paper
• Alignment — 6× in this paper · explained in 1 episode
• Accuracy — 4× in this paper · explained in 1 episode
• Clustering — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Anisotropy — 3× in this paper · explained in 3 episodes
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Gradient Flow — 2× in this paper · explained in 2 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Activation Function — 1× in this paper · explained in 1 episode
• Ambient Dimension — 1× in this paper · explained in 1 episode
• Application of the Data Processing Inequality — 1× in this paper
• Degeneracy — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In Advances in Neural Information Processing Systems — 1× in this paper
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
• Improved Baselines with Momentum Contrastive Learning
• Variance-Covariance Regularization Improves Representation Learning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models