Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasets
Learning-state-aware dynamic generative data augmentation (LSADA) is proposed, which introduces a decoupled data augmentation and diffusion fusion strategy that applies strength-controlled transformations to class-relevant regions and generates diverse class-irrelevant regions, progressively fusing them to improve imag...
Ting Xiang, Chen-Xi Deng, Jinhui Zhao et al.
· 0 citations