Profiles2021-2026
Gang Niu
RIKEN
20Papers
0Last author
37Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers20
- Rethinking Consistent Multi-Label Classification Under Inexact SupervisionAuthor 4 of 5ICLR 2026 · 3 citations
- Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning AlgorithmsAuthor 5 of 6ICLR 2026 · 2 citations
- Learning from Label Proportions via Proportional Value ClassificationAuthor 4 of 5ICLR 2026
- Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label ClassificationAuthor 4 of 5ICLR 2026
- Realistic Evaluation of Deep Partial-Label Learning AlgorithmsAuthor 4 of 6ICLR 2025
- What Makes Partial-Label Learning Algorithms Effective?Author 6 of 9NeurIPS 2024 · 7 citations
- Diversified Outlier Exposure for Out-of-Distribution Detection via Informative ExtrapolationAuthor 5 of 7NeurIPS 2023 · 54 citations
- Distribution Shift Matters for Knowledge Distillation with Webly Collected ImagesAuthor 3 of 5ICCV 2023 · 21 citations
- Binary Classification with Confidence DifferenceAuthor 4 of 6NeurIPS 2023 · 20 citations
- Generalizing Importance Weighting to A Universal Solver for Distribution Shift ProblemsAuthor 3 of 4NeurIPS 2023 · 17 citations
- Multi-Label Knowledge DistillationAuthor 5 of 7ICCV 2023 · 16 citations
- Towards Effective Visual Representations for Partial-Label LearningAuthor 4 of 5CVPR 2023
- Reliable Adversarial Distillation with Unreliable TeachersAuthor 6 of 9ICLR 2022 · 92 citations
- Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix EstimationAuthor 6 of 8CVPR 2022 · 63 citations
- Meta Discovery: Learning to Discover Novel Classes given Very Limited DataAuthor 7 of 9ICLR 2022 · 52 citations
- Federated Learning from Only Unlabeled Data with Class-conditional-sharing ClientsAuthor 4 of 6ICLR 2022 · 44 citations
- Learning Contrastive Embedding in Low-Dimensional SpaceAuthor 5 of 6NeurIPS 2022 · 26 citations
- Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative AttacksAuthor 5 of 7NeurIPS 2022 · 14 citations
- Probabilistic Margins for Instance Reweighting in Adversarial TrainingAuthor 6 of 8NeurIPS 2021 · 84 citations
- Large-Margin Contrastive Learning with Distance Polarization RegularizerAuthor 2 of 6ICML 2021 · 48 citations
