用随机掩码提升神经网络置信度与准确率的一致性
Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
- 通过随机稀疏掩码动态调整模型置信度
- 在数据损坏下仍保持优异校准性能
- 适合对可靠性要求高的医疗自动驾驶场景
近年来，深度神经网络在诸多领域表现优异。然而，在自动驾驶、医疗等安全关键场景中，其置信度估计常不可靠，可能导致严重后果。现有方法多聚焦于修改分类器，但对导致低估信心的校准误差关注不足。为此，本文提出MaC-Cal，一种基于掩码的校准方法，利用随机稀疏性增强置信度与准确率的一致性。该方法采用两阶段训练，结合自适应稀疏度，根据置信度与准确率的偏差动态调整掩码保留率。大量实验表明，MaC-Cal在数据污染下仍具备优越的校准性能与鲁棒性，为DNN可靠置信度估计提供了一种实用有效方案。
原文摘要 · Abstract (English)
In recent years, deep neural networks (DNNs) have shown competitive results in many fields. Despite this success, they often suffer from poor calibration, especially in safety-critical scenarios such as autonomous driving and healthcare, where unreliable confidence estimates can lead to serious consequences. Recent studies have focused on improving calibration by modifying the classifier, yet such efforts remain limited. Moreover, most existing approaches overlook calibration errors caused by underconfidence, which can be equally detrimental. To address these challenges, we propose MaC-Cal, a novel mask-based classifier calibration method that leverages stochastic sparsity to enhance the alignment between confidence and accuracy. MaC-Cal adopts a two-stage training scheme with adaptive sparsity, dynamically adjusting mask retention rates based on the deviation between confidence and accuracy. Extensive experiments show that MaC-Cal achieves superior calibration performance and robustness under data corruption, offering a practical and effective solution for reliable confidence estimation in DNNs.
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。