Radial Basis Function Networks as Projection Heads in Self-Supervised Learning
cs.CV, cs.LG
Submitted: 2026-06-19
Updated: 2026-11-03
Code: https://github.com/andreas-schliebitz/rbfn-ssl-projector
Terminology
Sources
- Reverse Engineering Self-Supervised Learning
- Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning
- Improved Baselines with Momentum Contrastive Learning
- Understanding and Improving the Role of Projection Head in Self-Supervised Learning
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions
- Representation Learning with Contrastive Predictive Coding
- InfoNCE Loss Provably Learns Cluster-Preserving Representations
- Towards the Sparseness of Projection Head in Self-Supervised Learning
- LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
- Deep Kernel Learning
- Investigating the Benefits of Projection Head for Representation Learning
- Deep-RBF Networks Revisited: Robust Classification with Rejection
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs