English

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

Computer Vision and Pattern Recognition 2026-05-25 v1

Abstract

Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing methods partially address these issues but typically ignore the non-uniform impact of label noise across classes, resulting in ineffective correction for tail classes and over-regularization for head classes. To address this issue, we propose Class-Adaptive Rectification with Experts (CARE), a parameter-efficient framework that leverages three complementary supervision sources from vision-language models (VLM): observed noisy labels, VLM text embeddings, and visual features. CARE introduces a class-adaptive expert consensus mechanism that enforces stricter agreement for tail classes and more permissive agreement for head classes based on class frequency. By aggregating high-confidence predictions across these sources, CARE filters unreliable signals and recalibrates class distributions, yielding more reliable rectification under long-tailed distributions. Extensive experiments on both synthetic and real-world benchmarks demonstrate that CARE consistently outperforms state-of-the-art methods, achieving up to 3.0\% performance gains. The source code is available at https://github.com/qwq123-study/CARE.

Keywords

Cite

@article{arxiv.2605.23254,
  title  = {CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels},
  author = {Mengke Li and Haiquan Ling and Lihao Chen and Yang Lu and Yiqun Zhang and Hui Huang},
  journal= {arXiv preprint arXiv:2605.23254},
  year   = {2026}
}

Comments

poster in ICML 2026

R2 v1 2026-07-22T07:27:39.208Z