 From Shortcuts to Triggers: Backdoor Defense with Denoised PoENorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 |
 Mitigating Memorization of Noisy Labels by Clipping the Model PredictionInternational Conference on Machine Learning (ICML), 2022 |
 Open-Sampling: Exploring Out-of-Distribution data for Re-balancing
Long-tailed datasetsInternational Conference on Machine Learning (ICML), 2022 |
 Open-set Label Noise Can Improve Robustness Against Inherent Label NoiseNeural Information Processing Systems (NeurIPS), 2021 |
 Combating noisy labels by agreement: A joint training method with
co-regularizationComputer Vision and Pattern Recognition (CVPR), 2020 |