通过截断特征值提升模型不确定性估计准确性
Feature Clipping for Uncertainty Calibration
- 截断高维特征值以增加高误差样本的熵
- 在多个数据集上显著改善模型校准性能
- 首个基于特征修改的校准方法，适合可靠性要求高的场景
深度神经网络在各类任务中取得显著成功，但可靠的不确定性估计（即模型校准）对于其安全有效部署至关重要。现代DNN常表现出过度自信，导致校准偏差。本文提出一种新型后处理校准方法——特征截断（FC），通过将特征值截断至指定阈值，有效提升高校准误差样本的熵，同时保留低误差样本的信息。该过程降低预测过度自信，改善模型整体校准性能。在CIFAR-10、CIFAR-100和ImageNet等数据集，以及CNN与Transformer等多种模型上的广泛实验表明，FC持续提升校准效果。此外，我们提供了理论分析验证方法有效性。作为首个基于特征修改的校准技术，特征截断显著优于后处理与训练时校准方法，开创了特征级校准的新路径。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) have achieved significant success across various tasks, but ensuring reliable uncertainty estimates, known as model calibration, is crucial for their safe and effective deployment. Modern DNNs often suffer from overconfidence, leading to miscalibration. We propose a novel post-hoc calibration method called feature clipping (FC) to address this issue. FC involves clipping feature values to a specified threshold, effectively increasing entropy in high calibration error samples while maintaining the information in low calibration error samples. This process reduces the overconfidence in predictions, improving the overall calibration of the model. Our extensive experiments on datasets such as CIFAR-10, CIFAR-100, and ImageNet, and models including CNNs and transformers, demonstrate that FC consistently enhances calibration performance. Additionally, we provide a theoretical analysis that validates the effectiveness of our method. As the first calibration technique based on feature modification, feature clipping offers a novel approach to improving model calibration, showing significant improvements over both post-hoc and train-time calibration methods and pioneering a new avenue for feature-based model calibration.
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。