Skip to content
conftrace_
2024 ICML ICML 2024

DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Zelin Zang, Hao Luo, Kai Wang, Panpan Zhang, Fan Wang, Stan Z. Li, Yang You

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Learning Types > Self-Supervised Learning Deep Learning > Models > Diffusion Models

Keywords

data augmentation diffusion model representation ability conditional diffusion semantic encoder unsupervised contrastive learning
Download PDF