通过自适应校准提升安全半监督学习的可靠性
CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning
- 提出自适应标签平滑与温度缩放，统一校准分类器和异常检测器
- 在多个数据集上显著降低错误伪标签率，提升安全半监督性能
- 适合关注模型鲁棒性与真实场景部署的研究者
半监督学习（SSL）利用未标记数据提升模型性能，但实际应用中常面临标签分布不匹配问题：未标记数据包含训练集中不存在的真实标签。现有安全半监督方法结合分类与分布外（OOD）检测，但深度神经网络的过度自信会导致错误伪标签或误判OOD。为此，本文提出新方法CaliMatch，同时校准分类器与OOD检测器。CaliMatch采用自适应标签平滑与温度缩放，无需手动调节平滑程度即可实现有效校准。我们从理论上证明，在安全半监督中同时优化两类模型校准的重要性。在CIFAR-10、CIFAR-100、SVHN、TinyImageNet和ImageNet上的大量实验表明，CaliMatch在安全半监督任务中优于现有方法。
原文摘要 · Abstract (English)
Semi-supervised learning (SSL) uses unlabeled data to improve the performance of machine learning models when labeled data is scarce. However, its real-world applications often face the label distribution mismatch problem, in which the unlabeled dataset includes instances whose ground-truth labels are absent from the labeled training dataset. Recent studies, referred to as safe SSL, have addressed this issue by using both classification and out-of-distribution (OOD) detection. However, the existing methods may suffer from overconfidence in deep neural networks, leading to increased SSL errors because of high confidence in incorrect pseudo-labels or OOD detection. To address this, we propose a novel method, CaliMatch, which calibrates both the classifier and the OOD detector to foster safe SSL. CaliMatch presents adaptive label smoothing and temperature scaling, which eliminates the need to manually tune the smoothing degree for effective calibration. We give a theoretical justification for why improving the calibration of both the classifier and the OOD detector is crucial in safe SSL. Extensive evaluations on CIFAR-10, CIFAR-100, SVHN, TinyImageNet, and ImageNet demonstrate that CaliMatch outperforms the existing methods in safe SSL tasks.
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。