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

2026-05-22

AI Summary

Real-world data often exhibit both long-tailed distributions and non-uniform label noise, with tail classes particularly susceptible to noisy annotations. To address this challenge, this work proposes the CARE framework, which introduces, for the first time, a class-adaptive expert consensus mechanism. CARE integrates three types of supervision signals—noisy labels, textual embeddings, and visual features—derived from vision-language models, imposing stronger consistency constraints on tail classes while moderately relaxing them for head classes to achieve precise and balanced label correction. Extensive experiments demonstrate that CARE significantly outperforms existing methods across multiple synthetic and real-world benchmarks, achieving performance gains of up to 3.0%.

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.

Problem

• long-tailed distribution
• noisy labels
• class imbalance
• label noise
• tail classes

Innovation

• Class-Adaptive Consensus
• Long-Tailed Learning
• Noisy Label Correction
• Vision-Language Models
• Expert Aggregation