Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many recently proposed approaches to mitigate this have demonstrated substantial progress in improving DNN calibration. However, they hardly touch upon refinement, which historically has been an essential aspect of calibration. Refinement indicates separability of a network's correct and incorrect predictions. This paper presents a theoretically and empirically supported exposition reviewing refinement of a calibrated model. Firstly, we show the breakdown of expected calibration error (ECE), into predicted confidence and refinement under the assumption of over-confident predictions. Secondly, linking with this result, we highlight that regularization based calibration only focuses on naively reducing a model's confidence. This logically has a severe downside to a model's refinement as correct and incorrect predictions become tightly coupled. Lastly, connecting refinement with ECE also provides support to existing refinement based approaches which improve calibration but do not explain the reasoning behind it. We support our claims through rigorous empirical evaluations of many state of the art calibration approaches on widely used datasets and neural networks. We find that many calibration approaches with the likes of label smoothing, mixup etc. lower the usefulness of a DNN by degrading its refinement. Even under natural data shift, this calibration-refinement trade-off holds for the majority of calibration methods.
Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference
King’s Communications, Learning & Information Processing (KCLIP) lab（国王通讯、学习与信息处理（KCLIP）实验室）；Centre for Intelligent Information Processing Systems (CIIPS)（智能信息处理系统中心）；Department of Engineering, King’s College London（伦敦国王学院工程系）
Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors
KU Leuven（鲁汶大学）；German Cancer Research Center (DKFZ)（德国癌症研究中心）；German Cancer Consortium (DKTK)（德国癌症联盟）；Goethe University Frankfurt（法兰克福大学）；University of Oulu（奥卢大学）；Frankfurt Cancer Institute（法兰克福癌症研究所）
DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability
University of Florida (UF)（佛罗里达大学）；Torch Technologies, LLC（Torch科技有限责任公司）；McKnight Brain Institute（麦克奈特脑研究所）；College of Public Health and Health Professions（公共卫生与健康职业学院）；College of Medicine（医学院）；United States Air Force Research Laboratory（美国空军研究实验室）；Herbert Wertheim College of Engineering（赫伯特·韦特海姆工程学院）；Department of Biomedical Engineering（生物医学工程系）；Department of Clinical and Health Psychology（临床与健康心理学系）；Department of Neuroscience（神经科学系）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Computer Information and Science and Engineering（计算机信息与工程系）
Calibrated Multivariate Distributional Regression with Pre-Rank Regularization
Department of Statistics and Data Science, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE（统计与数据科学系，Mohamed Bin Zayed人工智能大学，阿布扎比，阿联酋）
Selective Learning: Towards Robust Calibration with Dynamic Regularization
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Rutgers University（罗格斯大学）；A*STAR Centre for Frontier AI Research (CFAR)（新加坡科技研究局前沿人工智能研究中心）
Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization
Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)
DataNova；U.S. Army Research Laboratory（美国陆军研究实验室）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；DCS Corp（DCS公司）；University of Technology, Sydney（悉尼科技大学）；National Chiao-Tung University（国立交通大学）
IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI
Nanchang University（南昌大学）；Medical AI Research Center, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院医学人工智能研究中心）
