Ching Lam CHOIDivCo uses contrastive learning to reduce mode collapse in GANs.
CVPR 2021
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
Related work
NeurIPS 2026Oral
Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality
Synthetic data is useful when it occupies the right real-image likelihood regimes; ELD measures energy shape to predict, diagnose, curate visual pretraining data.