Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowds [TPAMI 2024]
Uni-OVSeg: Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision [Preprint 2024]
Regularly Truncated M-estimators for Learning with Noisy Labels [TPAMI 2024]
IDEAL: Influence-driven Selective Annotations Empower In-context Learners in Large Language Models [ICLR 2024]
Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples [ICCV 2023]
Holistic Label Correction for Noisy Multi-Label Classification [ICCV 2023]
HumanMAC: Masked Motion Completion for Human Motion Prediction [ICCV 2023]
Robust Generalization against Corruptions via Worst-Case Sharpness Minimization [CVPR 2023]
Moderate Coreset: A Universal Method of Data Selection for Real-world Data-efficient Deep Learning [ICLR 2023]
Harnessing Out-of-Distribution Examples via Augmenting Content and Style [ICLR 2023]
A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond [ICLR 2023]
Pluralistic Image Completion with Gaussian Mixture Models [NeurIPS 2022]
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels [ICLR 2022]
Robust Early-learning: Hindering the Memorization of Noisy Labels [ICLR 2021]
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels [ICML 2021]
Part-dependent Label Noise: Towards Instance-dependent Label Noise [NeurIPS 2020]
Are Anchor Points Really Indispensable in Label-noise Learning? [NeurIPS 2019]
Estimating Noise Transition Matrix with Label Correlations for Noisy Multi-Label Learning [NeurIPS 2022]
Selective-Supervised Contrastive Learning with Noisy Labels [CVPR 2022]