论文标题
神经夹具：神经网络校准的联合输入扰动和温度缩放
Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration
论文作者
论文摘要
神经网络校准是深度学习的重要任务，以确保模型预测的信心与真实的正确性可能性之间的一致性。在本文中，我们提出了一种称为Neural夹紧的新的后处理校准方法，该方法通过可学习的通用输入扰动和输出温度扩展参数在预训练的分类器上采用简单的联合输入输出转换。此外，我们提供了理论上的解释，说明为什么神经夹具比温度缩放更好。在血液中，CIFAR-100和ImageNet图像识别数据集以及各种深神经网络模型上进行了评估，我们的经验结果表明，神经夹具明显胜过最先进的后加工校准方法。该代码可在github.com/yungchentang/nctoolkit上找到，该演示可在huggingface.co/spaces/trustsafeai/nctv上获得。
Neural network calibration is an essential task in deep learning to ensure consistency between the confidence of model prediction and the true correctness likelihood. In this paper, we propose a new post-processing calibration method called Neural Clamping, which employs a simple joint input-output transformation on a pre-trained classifier via a learnable universal input perturbation and an output temperature scaling parameter. Moreover, we provide theoretical explanations on why Neural Clamping is provably better than temperature scaling. Evaluated on BloodMNIST, CIFAR-100, and ImageNet image recognition datasets and a variety of deep neural network models, our empirical results show that Neural Clamping significantly outperforms state-of-the-art post-processing calibration methods. The code is available at github.com/yungchentang/NCToolkit, and the demo is available at huggingface.co/spaces/TrustSafeAI/NCTV.
