cs.LGAug 26, 2021

Robust Long-Tailed Learning under Label Noise

Authors: Tong Wei, Jiang-Xin Shi, Min-Ling Zhang, Yu-Feng Li

Organizations: Nanjing University, China

Abstract

Long-tailed learning aims to enhance the generalization performance of underrepresented tail classes. However, previous methods have largely overlooked the prevalence of noisy labels in training data. In this paper, we address the challenge of noisy labels in long-tailed learning. We identify a critical issue: the commonly used small-loss noisy label detection criterion fails to perform effectively in long-tailed class distributions. This failure arises from the inherent bias of deep neural networks, which tend to misclassify tail class examples as head classes, leading to unreliable loss calculations. To mitigate this, we propose a novel small-distance criterion that leverages the robustness of learned representations, enabling more accurate identification of correctly-labeled examples across both head and tail classes. Additionally, to improve training for tail classes, we replace discrete pseudo-labels with label distributions for examples flagged as noisy, resulting in significant performance gains. Based on these contributions, we introduce the Robust Long-Tail learning framework, designed to train models that are resilient to both class imbalance and noisy labels. Extensive experiments on benchmark and real-world datasets demonstrate that our approach outperforms previous methods, offering substantial performance improvements.

Figures & tables

Explore similar work

CardsList
  1. CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels

    May 22, 2026Mengke Li, Haiquan Ling, Lihao Chen +3Class-Imbalanced LearningLearning with Noisy Labels

  2. When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling

    Sep 27, 2026Ping Guo, Zhiqi Huang, Xinran LiImage SegmentationLong-Tail Learning

  3. Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label

    Apr 25, 2026Mengke Li, Haiquan Ling, Yiqun Zhang +2Long-Tail LearningLearning with Noisy Labels