Post-hoc Uncertainty Calibration for Domain Drift Scenarios
Technical University of Munich（慕尼黑工业大学）；Siemens AG（西门子股份公司）；German Cancer Consortium（德国癌症联盟）；German Cancer Research Center Heidelberg（海德堡德国癌症研究中心）；Frankfurt University（法兰克福大学）
Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, Florian Buettner
We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representative of the true likelihood of a prediction can be achieved using post-hoc calibration methods. However, to date the focus of these approaches has been on in-domain calibration. Our contribution is two-fold. First, we show that existing post-hoc calibration methods yield highly over-confident predictions under domain shift. Second, we introduce a simple strategy where perturbations are applied to samples in the validation set before performing the post-hoc calibration step. In extensive experiments, we demonstrate that this perturbation step results in substantially better calibration under domain shift on a wide range of architectures and modelling tasks.
In many applications, it is desirable that a classifier not only makes accurate predictions, but also outputs calibrated posterior probabilities. However, many existing classifiers, especially deep neural network classifiers, tend to be uncalibrated. Post-hoc calibration is a technique to recalibrate a model by learning a calibration map. Existing approaches mostly focus on constructing calibration maps with low calibration errors, however, this quality is inadequate for a calibrator being useful. In this paper, we introduce two constraints that are worth consideration in designing a calibrati…
Technical University of Munich（慕尼黑工业大学）；German Cancer Research Center (DKFZ)（德国癌症研究中心（DKFZ））；Goethe University Frankfurt（法兰克福歌德大学）
We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS). Standard deep neural networks typically yield uncalibrated predictions, which can be transformed into calibrated confidence scores using post-hoc calibration methods. In this contribution, we demonstrate that the performance of accuracy-preserving state-of-the-art post-hoc calibrators is limited by their intrinsic expressive power. We generalize temperature scaling by computing prediction-specific temperatures, parameterized by a neural network. We show with exten…
We introduce the notion of heterogeneous calibration that applies a post-hoc model-agnostic transformation to model outputs for improving AUC performance on binary classification tasks. We consider overconfident models, whose performance is significantly better on training vs test data and give intuition onto why they might under-utilize moderately effective simple patterns in the data. We refer to these simple patterns as heterogeneous partitions of the feature space and show theoretically that perfectly calibrating each partition separately optimizes AUC. This gives a general paradigm of het…
Australian National University（澳大利亚国立大学）；Google Research（谷歌研究院）；DATA61, CSIRO（澳大利亚联邦科学与工业研究组织DATA61）
Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions are equally important as the decisions themselves. In recent years, there is a surge of research on neural network calibration and the majority of the works can be categorized into post-hoc calibration methods, defined as methods that learn an additional function to calibrate an already trained base network. In this work, we intend to understand the post-hoc calibration methods from a theoretical point of view. Especi…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；IBM Research（IBM研究院）
Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available. Modern Bayesian models, however, typically involve intractable posteriors that are approximated with, potentially crude, surrogates. This difficulty has engendered loss-calibrated techniques that aim to learn posterior approximations that favor high-utility decisions. In this paper, focusing on Bayesian neural networks, we develop methods for correcting approximate posterior predictive distributions encouraging them to prefer high-utility decisions…
ANU（澳大利亚国立大学）；ACRV（澳大利亚机器人视觉中心）；Georgia Tech（佐治亚理工学院）；Microsoft Research（微软研究院）；Google Research（谷歌研究院）；University of Washington（华盛顿大学）
Predicting calibrated confidence scores for multi-class deep networks is important for avoiding rare but costly mistakes. A common approach is to learn a post-hoc calibration function that transforms the output of the original network into calibrated confidence scores while maintaining the network's accuracy. However, previous post-hoc calibration techniques work only with simple calibration functions, potentially lacking sufficient representation to calibrate the complex function landscape of deep networks. In this work, we aim to learn general post-hoc calibration functions that can preserve…
TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation
ICube Laboratory, CNRS UMR-7357, University of Strasbourg（ICube实验室，CNRS UMR-7357，斯特拉斯堡大学）；CLCC Institut Strauss（CLCC斯特拉斯堡研究所）；German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing（海德堡德国癌症研究中心（DKFZ），医学图像计算部门）；Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital（放射肿瘤科，海德堡大学医院模式分析与学习小组）；Medical Faculty Heidelberg, Heidelberg University（海德堡医学系，海德堡大学）
Idiap Research Institute（Idiap研究所）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
This paper addresses the problem of ad hoc microphone array calibration where only partial information about the distances between microphones is available. We construct a matrix consisting of the pairwise distances and propose to estimate the missing entries based on a novel Euclidean distance matrix completion algorithm by alternative low-rank matrix completion and projection onto the Euclidean distance space. This approach confines the recovered matrix to the EDM cone at each iteration of the matrix completion algorithm. The theoretical guarantees of the calibration performance are obtained…
University at Buffalo（布法罗大学）；Penn State Erie（宾夕法尼亚州立大学伊利分校）
Deep Neural Networks (DNNs), despite their tremendous success in recent years, could still cast doubts on their predictions due to the intrinsic uncertainty associated with their learning process. Ensemble techniques and post-hoc calibrations are two types of approaches that have individually shown promise in improving the uncertainty calibration of DNNs. However, the synergistic effect of the two types of methods has not been well explored. In this paper, we propose a truth discovery framework to integrate ensemble-based and post-hoc calibration methods. Using the geometric variance of the en…
Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been developed to improve the calibration of their predictive uncertainty both during training and post-hoc. In this work, we propose differentiable losses to improve calibration based on a soft (continuous) version of the binning operation underlying popular calibration-error estimators. When incorporated into training, these soft calibration losses achieve sta…
Rethinking Post-Hoc Calibration in Semantic Segmentation
ICube Laboratory, CNRS UMR 7357, University of Strasbourg（斯特拉斯堡大学ICube实验室，CNRS UMR 7357）；CLCC Institut Strauss（斯特劳斯研究所）；German Cancer Research Center (DKFZ)（德国癌症研究中心）；Faculty of Mathematics and Computer Science, University of Heidelberg（海德堡大学数学与计算机科学学院）；Medical Faculty Heidelberg, Heidelberg University（海德堡大学医学院）；Pattern Analysis and Learning Group, Dept. of Radiation Oncology, Heidelberg University Hospital（海德堡大学医院放射肿瘤科模式分析与学习组）
Tsinghua University（清华大学）；University of Notre Dame（圣母大学）
Temporal drift of sensory data is a severe problem impacting the data quality of wireless sensor networks (WSNs). With the proliferation of large-scale and long-term WSNs, it is becoming more important to calibrate sensors when the ground truth is unavailable. This problem is called "blind calibration". In this paper, we propose a novel deep learning method named projection-recovery network (PRNet) to blindly calibrate sensor measurements online. The PRNet first projects the drifted data to a feature space, and uses a powerful deep convolutional neural network to recover the estimated drift-fr…
To increase the trustworthiness of deep neural network (DNN) classifiers, an accurate prediction confidence that represents the true likelihood of correctness is crucial. Towards this end, many post-hoc calibration methods have been proposed to leverage a lightweight model to map the target DNN's output layer into a calibrated confidence. Nonetheless, on an out-of-distribution (OOD) dataset in practice, the target DNN can often mis-classify samples with a high confidence, creating significant challenges for the existing calibration methods to produce an accurate confidence. In this paper, we p…
FeatCal: Feature Calibration for Post-Merging Models
The Hong Kong Polytechnic University (PolyU)（香港理工大学）；The Chinese University of Hong Kong（香港中文大学）；PolyU-Daya Bay Technology and Innovation Research Institute（PolyU-大亚湾技术与创新研究院）
In this paper, we study the post-hoc calibration of modern neural networks, a problem that has drawn a lot of attention in recent years. Many calibration methods of varying complexity have been proposed for the task, but there is no consensus about how expressive these should be. We focus on the task of confidence scaling, specifically on post-hoc methods that generalize Temperature Scaling, we call these the Adaptive Temperature Scaling family. We analyse expressive functions that improve calibration and propose interpretable methods. We show that when there is plenty of data complex models l…
Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models
Department of Computer Science and Engineering, Visvesvaraya Technological University, Belagavi（维斯瓦拉亚科技大学计算机科学与工程系，贝拉加维）；Department of Computer Science and Business System, SG Balekundri Institute of Technology, Belagavi（SG巴莱昆德里理工学院计算机科学与商业系统系，贝拉加维）
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；IIIS, Tsinghua University（清华大学交叉信息研究院）；Tencent（腾讯）
It is often observed that the probabilistic predictions given by a machine learning model can disagree with averaged actual outcomes on specific subsets of data, which is also known as the issue of miscalibration. It is responsible for the unreliability of practical machine learning systems. For example, in online advertising, an ad can receive a click-through rate prediction of 0.1 over some population of users where its actual click rate is 0.15. In such cases, the probabilistic predictions have to be fixed before the system can be deployed. In this paper, we first introduce a new evaluation…
San Diego State University（圣地亚哥州立大学）；Perelman School of Medicine at the University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）；University of Pennsylvania（宾夕法尼亚大学）；Google（谷歌）；Helix
This paper investigates the post-hoc calibration of confidence for "exploratory" machine learning classification problems. The difficulty in these problems stems from the continuing desire to push the boundaries of which categories have enough examples to generalize from when curating datasets, and confusion regarding the validity of those categories. We argue that for such problems the "one-versus-all" approach (top-label calibration) must be used rather than the "calibrate-the-full-response-matrix" approach advocated elsewhere in the literature. We introduce and test four new algorithms desi…
h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective
Research Inst. of Trustworthy Autonomous Systems & Dept. of Computer Science and Engineering, SUSTech, China（可信自主系统研究所及计算机科学与工程系，深圳技术大学，中国）；Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Dept. of Computer Science and Engineering, SUSTech, and Peng Cheng Lab, China（脑启发智能计算广东省重点实验室、计算机科学与工程系，深圳技术大学，以及鹏城实验室，中国）；Faculty of Engineering and Information Technology, University of Technology Sydney, Australia（工程与信息技术学院，悉尼大学，澳大利亚）；Inst. of Biomedical Engineering, Dept. of Engineering Science, University of Oxford, UK（生物医学工程研究所、工程科学系，牛津大学，英国）
Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs
Department of Statistics and Data Science, Southern University of Science and Technology（统计与数据科学系，南方科技大学）；School of Computing, National University of Singapore（计算学院，新加坡国立大学）；Department of Computer Sciences, University of Wisconsin-Madison（计算机科学系，威斯康星大学麦迪逊分校）；College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）
RIKEN AIP（理化学研究所人工智能项目）；Kumamoto University Hospital（熊本大学医院）；Kumamoto University（熊本大学）；The University of Tokyo（东京大学）；ThinkCyte（ThinkCyte公司）
We propose an evaluation framework for class probability estimates (CPEs) in the presence of label uncertainty, which is commonly observed as diagnosis disagreement between experts in the medical domain. We also formalize evaluation metrics for higher-order statistics, including inter-rater disagreement, to assess predictions on label uncertainty. Moreover, we propose a novel post-hoc method called $alpha$-calibration, that equips neural network classifiers with calibrated distributions over CPEs. Using synthetic experiments and a large-scale medical imaging application, we show that our appro…
A Hybrid Machine Learning Approach for Synthetic Data Generation with Post Hoc Calibration for Clinical Tabular Datasets
organization= Department of Electrical \& Electronic Engineering, Bangladesh University of Business；organization= Department of Electrical Engineering；Computer Science, University of Michigan , country= United States
