Zhihao Zhou

Content Diversity-guided Ambiguity Mitigation for Open-Set Noisy Label Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Open-set noisy label learning faces a critical challenge in maintaining robust DNN performance when training data contain both in-distribution noisy (IDN) and out-of-distribution (OOD) samples. These noisy samples induce overconfident but erroneous predictions due to …