| Understanding and improving early stopping for learning with noisy labels Y Bai, E Yang, B Han, Y Yang, J Li, Y Mao, G Niu, T Liu Advances in Neural Information Processing Systems 34, 24392-24403, 2021 | 204 | 2021 |
| Me-momentum: Extracting hard confident examples from noisily labeled data Y Bai, T Liu Proceedings of the IEEE/CVF international conference on computer vision …, 2021 | 39 | 2021 |
| Biomedical image analysis competitions: The state of current participation practice M Eisenmann, A Reinke, V Weru, MD Tizabi, F Isensee, TJ Adler, ... arXiv preprint arXiv:2212.08568, 2022 | 28 | 2022 |
| RSA: reducing semantic shift from aggressive augmentations for self-supervised learning Y Bai, E Yang, Z Wang, Y Du, B Han, C Deng, D Wang, T Liu Advances in Neural Information Processing Systems 35, 21128-21141, 2022 | 14* | 2022 |
| QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge H Bran, F Navarro, I Ezhov, A Bayat, D Das, F Kofler, S Shit, ... arXiv preprint arXiv:2405.18435, 2024 | 1 | 2024 |
| Subclass-dominant label noise: a counterexample for the success of early stopping Y Bai, Z Han, E Yang, J Yu, B Han, D Wang, T Liu Advances in Neural Information Processing Systems 36, 2024 | 1 | 2024 |
| Robust Representation Learning: Understanding the Role of Early Stopping amidst Noisy Labels Y Bai | | 2024 |
Tongliang LiuDirector, Sydney AI Centre, University of Sydney & Mohamed bin Zayed University of AIVerified email at sydney.edu.au
