Boosting Class Representation via Semantically Related Instances for Robust Long-Tailed Learning with Noisy Labels
Yuhang Li, Zhuying Li, Yuheng Jia
2025Year
3Citations
6Top-tier citations
Abstract
The problem of learning from long-tailed noisy data, referred to as Long-Tailed Noisy Label Learning (LTNLL), presents significant challenges in deep learning. LTNLL datasets are typically affected by two primary issues:
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext cd803050-fa79-4658-9c2d-f0b1a74936f0Cited by top-tier papers6
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised LearningYaxin Hou, Bo Han, Yuheng Jia, Hui Liu et al.NeurIPS 2025 · 4 citations
- Reframing Long-Tailed Learning via Loss Landscape GeometryShenghan Chen, Yiming Liu, Yanzhen Wang, Yujia Wang et al.CVPR 2026 · 2 citations
- Class-Prior Perturbation-Robust Regularization for Imbalanced Unreliable Partial Label LearningCongyu Qiao, Haohao Dong, Xin Geng, Ning XuICML 2026
- Robust Label Proportions LearningJueyu Chen, Wantao Wen, Yeqiang Wang, Erliang Lin et al.NeurIPS 2025
- CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy LabelsMengke Li, Haiquan Ling, Lihao Chen, Yang Lu et al.ICML 2026
Builds on23
- Decoupling Representation and Classifier for Long-Tailed RecognitionBingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan et al.ICLR 2020 · 1,496 citations
- DivideMix: Learning with Noisy Labels as Semi-supervised LearningJunnan Li, Richard Socher, Steven C. H. HoiICLR 2020 · 1,326 citations
- Symmetric Cross Entropy for Robust Learning With Noisy LabelsYisen Wang, Xingjun Ma, Zaiyi Chen, Yuan Luo et al.ICCV 2019 · 1,125 citations
- Balanced Meta-Softmax for Long-Tailed Visual RecognitionJiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma et al.NeurIPS 2020 · 861 citations
- Early-Learning Regularization Prevents Memorization of Noisy LabelsSheng Liu, Jonathan Niles-Weed, Narges Razavian, Carlos Fernandez-GrandaNeurIPS 2020 · 798 citations
Related papers
- Robust Logit Adjustment for Learning with Long-Tailed Noisy DataMingcai Chen, Yuntao Du, Wenyu Jiang, Baoming Zhang et al.AAAI 2025 · 4 citations
- Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed DataChen Shu, Hongjun Xu, Ruichi Zhang, Mengke Li et al.NeurIPS 2025
- Label-Noise Learning with Intrinsically Long-Tailed DataYang Lu, Yiliang Zhang, Bo Han, Yiu-Ming Cheung et al.ICCV 2023 · 32 citations
- Geometry of Long-Tailed Representation Learning: Rebalancing Features for Skewed DistributionsLingjie Yi, Jiachen Yao, Weimin Lyu, Haibin Ling et al.ICLR 2025
- Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation PerspectiveJialun Liu, Yifan Sun, Chuchu Han, Zhaopeng Dou et al.CVPR 2020
