Miscalibration-the mismatch between predicted probability and the true correctness likelihood-has been frequently identified in modern deep neural networks. Recent work in the field aims to address this problem by training calibrated models directly by optimizing a proxy of the calibration error alongside the conventional objective. Recently, Meta-Calibration (MC) showed the effectiveness of using meta-learning for learning better calibrated models. In this work, we extend MC with two main components: (1) gamma network (gamma-net), a meta network to learn a sample-wise gamma at a continuous space for focal loss for optimizing backbone network; (2) smooth expected calibration error (SECE), a Gaussian-kernel based unbiased and differentiable ECE which aims to smoothly optimizing gamma-net. The proposed method regularizes neural network towards better calibration meanwhile retain predictive performance. Our experiments show that (a) learning sample-wise gamma at continuous space can effectively perform calibration; (b) SECE smoothly optimise gamma-net towards better robustness to binning schemes; (c) the combination of gamma-net and SECE achieve the best calibration performance across various calibration metrics and retain very competitive predictive performance as compared to multiple recently proposed methods on three datasets.
翻译:摘要:当深度神经网络预测的概率与真实正确性可能性之间存在不匹配时,往往会出现误校准(miscalibration)的情况。近期该领域的工作旨在通过直接训练经过优化校准误差代理的校准模型来解决这个问题。最近,Meta-Calibration(MC)提出使用元学习(meta-learning)来学习更好的校准模型,显示了其有效性。在本文中,我们通过两个主要组件扩展了MC:(1)gamma网络(gamma-net),一个元神经网络,用于在连续空间学习样本特定的gamma值,以进行针对主干网络的focal loss的优化;(2)平滑期望校准误差(SECE),一种基于高斯核的无偏和可微的ECE,旨在平滑优化gamma-net。所提出的方法将神经网络正则化为更好的校准结果,同时保持预测性能。我们的实验表明:(a)在连续空间学习样本特定的gamma值可以有效进行校准;(b)SECE可以使gamma-net更具鲁棒性,以适应更多的分箱方案;(c) 结合gamma-net和SECE,相对于三个数据集上多个最近提出的方法,可以获得最佳的校准性能,并保持非常具竞争力的预测性能。