通过校准伪标签可信度，提升半监督多标签学习性能
DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning
- 根据伪标签正确性概率动态调整权重
- 在多个数据集上提升性能，最高超基线4.27%
- 适合标签稀缺的多标签场景
半监督多标签学习（SSMLL）旨在利用未标注数据缓解多标签学习中标签数据不足的问题。尽管伪标签已成为主流策略，但现有方法对所有伪标签赋予相同权重，可能放大噪声预测的影响，降低整体性能。本文理论验证了最优伪标签权重应反映其正确性概率。实证发现，同一数据集上未标注数据的正确性概率分布具有稳定性，即使标注样本数量变化也保持不变。基于此，我们提出分布校准伪标签（DiCaP），通过估计后验精确率来校准伪标签权重，并引入双阈值机制：高置信度样本被伪标注并加权，低置信度样本则通过无监督对比学习探索。在多个基准数据集上的实验表明，该方法持续提升性能，最高超越当前最优方法4.27%。
原文摘要 · Abstract (English)
Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data in multi-label learning (MLL) by leveraging unlabeled data to improve the model's performance. While pseudo-labeling has become a dominant strategy in SSMLL, most existing methods assign equal weights to all pseudo-labels regardless of their quality, which can amplify the impact of noisy or uncertain predictions and degrade the overall performance. In this paper, we theoretically verify that the optimal weight for a pseudo-label should reflect its correctness likelihood. Empirically, we observe that on the same dataset, the correctness likelihood distribution of unlabeled data remains stable, even as the number of labeled training samples varies. Building on this insight, we propose Distribution-Calibrated Pseudo-labeling (DiCaP), a correctness-aware framework that estimates posterior precision to calibrate pseudo-label weights. We further introduce a dual-thresholding mechanism to separate confident and ambiguous regions: confident samples are pseudo-labeled and weighted accordingly, while ambiguous ones are explored by unsupervised contrastive learning. Experiments conducted on multiple benchmark datasets verify that our method achieves consistent improvements, surpassing state-of-the-art methods by up to 4.27%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。