Contrastive Learning Comparison Hub
3 papers - avg viability 5.0
Top Papers
- Maximizing Incremental Information Entropy for Contrastive Learning(7.0)
IE-CL optimizes entropy gain in contrastive learning for improved representation performance.
- Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation(6.0)
Enhance visual representation in CLIP by integrating contrastive signals into diffusion-based reconstruction for better discriminative and perceptual ability.
- Asymptotic and Finite-Time Guarantees for Langevin-Based Temperature Annealing in InfoNCE(2.0)
The paper provides a theoretical framework for understanding temperature schedules in contrastive learning.