Study examines generative data augmentation for classifiers without external data
A new arXiv paper presents an empirical and theoretical study of generative data augmentation, adding samples from generative models to classifier training sets, focusing on deep networks without relying on externally pre-trained generators.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv stat.ML
Generative Data Augmentation Without External Data: An Empirical and Theoretical Study on Deep Networks