Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation.
This work proposes a single-stage, EM-style framework for generative noisy-label learning that is direction-agnostic and avoids explicit image synthesis, and introduces Partial-Label Supervision (PLS), an instance specific prior over clean labels that balances coverage and uncertainty, improving data-dependent regulari...