In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets. Despite this, the trained object detectors typically do not reliably assess uncertainty regarding their own knowledge, and the quality of their probabilistic predictions is usually poor. As these are often used to make subsequent decisions, such inaccurate probabilistic predictions must be avoided. In this work, we investigate the uncertainty calibration properties of different pretrained object detection architectures in a multi-class setting. We propose a framework to ensure a fair, unbiased, and repeatable evaluation and conduct detailed analyses assessing the calibration under distributional changes (e.g., distributional shift and application to out-of-distribution data). Furthermore, by investigating the influence of different detector paradigms, post-processing steps, and suitable choices of metrics, we deliver novel insights into why poor detector calibration emerges. Based on these insights, we are able to improve the calibration of a detector by simply finetuning its last layer.
Ruhr West University of Applied Sciences（鲁尔西部应用科技大学）；Elektronische Fahrwerksysteme GmbH（电子底盘系统有限公司）
Modern neural networks have found to be miscalibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision. Recent work has introduced methods for post-hoc confidence calibration for classification as well as for object detection to address this issue. Especially in safety critical applications, it is crucial to obtain a reliable self-assessment of a model. But what if the calibration method itself is uncertain, e.g., due to an insufficient knowledge base? We introduce Bayesian confidence calibration - a framework to obta…
The University of British Columbia（不列颠哥伦比亚大学）；Harvard Medical School（哈佛医学院）
Fully convolutional neural networks (FCNs), and in particular U-Nets, have achieved state-of-the-art results in semantic segmentation for numerous medical imaging applications. Moreover, batch normalization and Dice loss have been used successfully to stabilize and accelerate training. However, these networks are poorly calibrated i.e. they tend to produce overconfident predictions both in correct and erroneous classifications, making them unreliable and hard to interpret. In this paper, we study predictive uncertainty estimation in FCNs for medical image segmentation. We make the following co…
Bergische Universität Wuppertal（伍珀塔尔大学）；Hochschule Ruhr West（鲁尔西应用科学大学）
Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the according position and size information within a single frame. The performance of such an object detection model is important for the overall performance of the whole system. However, a detection model might also predict these objects under a certain degree of uncertainty. [...] In this work, we examine the semantic uncertainty (which object type?) as well as the spatial uncertai…
Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；The Hawkes Institute, University College London（霍克斯研究所，伦敦大学学院）；AI Laboratory, Massachusetts Institute of Technology（人工智能实验室，麻省理工学院）
ETH Zurich（苏黎世联邦理工学院）；INRIA Grenoble – Rhône-Alpes（法国国立信息学与自动化研究院格勒诺布尔-罗讷-阿尔卑斯分院）
It is well known that the accuracy of a calibration depends strongly on the choice of camera poses from which images of a calibration object are acquired. We present a system -- Calibration Wizard -- that interactively guides a user towards taking optimal calibration images. For each new image to be taken, the system computes, from all previously acquired images, the pose that leads to the globally maximum reduction of expected uncertainty on intrinsic parameters and then guides the user towards that pose. We also show how to incorporate uncertainty in corner point position in a novel principl…
Robert Bosch GmbH（罗伯特·博世有限公司）；Karlsruher Institute of Technology (KIT)（卡尔斯鲁厄理工学院（KIT））
Accurate camera calibration is a precondition for many computer vision applications. Calibration errors, such as wrong model assumptions or imprecise parameter estimation, can deteriorate a system's overall performance, making the reliable detection and quantification of these errors critical. In this work, we introduce an evaluation scheme to capture the fundamental error sources in camera calibration: systematic errors (biases) and uncertainty (variance). The proposed bias detection method uncovers smallest systematic errors and thereby reveals imperfections of the calibration setup and prov…
Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach
Université de technologie de Compiègne, CNRS, Heudiasyc（法国图卢兹工学院、CNRS、Heudiasyc）；CNRS, INSA Lyon, UCBL, LIRIS, UMR5205（CNRS、里昂国立应用科学学院、UCBL、LIRIS、UMR5205）
Most existing approaches to train a unified multi-organ segmentation model from several single-organ datasets require simultaneously access multiple datasets during training. In the real scenarios, due to privacy and ethics concerns, the training data of the organs of interest may not be publicly available. To this end, we investigate a data-free incremental organ segmentation scenario and propose a novel incremental training framework to solve it. We use the pretrained model instead of its own training data for privacy protection. Specifically, given a pretrained $K$ organ segmentation model …
Beyond Accuracy: Assessing Calibration of Geospatial Foundation Models and Their Sensitivity to Distribution Shifts
Technical University of Munich (TUM)（慕尼黑工业大学）；German Aerospace Center (DLR)（德国航空航天中心）；Massachusetts Institute of Technology (MIT)（麻省理工学院）；Taylor Geospatial（泰勒地理空间公司）
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；FZI Research Center for Information Technology（FZI信息技术研究中心）
In this paper, we present TEScalib, a novel extrinsic self-calibration approach of LiDAR and stereo camera using the geometric and photometric information of surrounding environments without any calibration targets for automated driving vehicles. Since LiDAR and stereo camera are widely used for sensor data fusion on automated driving vehicles, their extrinsic calibration is highly important. However, most of the LiDAR and stereo camera calibration approaches are mainly target-based and therefore time consuming. Even the newly developed targetless approaches in last years are either inaccurate…
Active domain adaptation (DA) aims to maximally boost the model adaptation on a new target domain by actively selecting limited target data to annotate, whereas traditional active learning methods may be less effective since they do not consider the domain shift issue. Despite active DA methods address this by further proposing targetness to measure the representativeness of target domain characteristics, their predictive uncertainty is usually based on the prediction of deterministic models, which can easily be miscalibrated on data with distribution shift. Considering this, we propose a \tex…
Imperial College London（帝国理工学院）；Samsung Research（三星研究院）
Curriculum learning needs example difficulty to proceed from easy to hard. However, the credibility of image difficulty is rarely investigated, which can seriously affect the effectiveness of curricula. In this work, we propose Angular Gap, a measure of difficulty based on the difference in angular distance between feature embeddings and class-weight embeddings built by hyperspherical learning. To ascertain difficulty estimation, we introduce class-wise model calibration, as a post-training technique, to the learnt hyperbolic space. This bridges the gap between probabilistic model calibration …
Despite achieving enormous success in predictive accuracy for visual classification problems, deep neural networks (DNNs) suffer from providing overconfident probabilities on out-of-distribution (OOD) data. Yet, accurate uncertainty estimation is crucial for safe and reliable robot autonomy. In this paper, we evaluate popular calibration techniques for open-set conditions in a way that is distinctly different from the conventional evaluation of calibration methods on OOD data. Our results show that closed-set DNN calibration approaches are much less effective for open-set recognition, which hi…
Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top performance, it is sometimes necessary to fine-tune the networks to the target environment. To this end, we propose a self-supervised domain calibration procedure based on robust pose graph optimization from Simultaneous Localization and Mapping (SLAM) as the supervision signal without requiring GPS or manual labeling. Moreover, we leverage the procedure to improve…
Microsoft Research Asia（微软亚洲研究院）；MILA（米拉研究所）；S-Lab, Nanyang Technological University（南洋理工大学S-Lab实验室）；Nanyang Technological University（南洋理工大学）
Confidence calibration is of great importance to the reliability of decisions made by machine learning systems. However, discriminative classifiers based on deep neural networks are often criticized for producing overconfident predictions that fail to reflect the true correctness likelihood of classification accuracy. We argue that such an inability to model uncertainty is mainly caused by the closed-world nature in softmax: a model trained by the cross-entropy loss will be forced to classify input into one of $K$ pre-defined categories with high probability. To address this problem, we for th…
Robert Bosch GmbH（罗伯特·博世股份有限公司）；Ulm University（乌尔姆大学）
Reliable uncertainty estimation is crucial for perception systems in safe autonomous driving. Recently, many methods have been proposed to model uncertainties in deep learning based object detectors. However, the estimated probabilities are often uncalibrated, which may lead to severe problems in safety critical scenarios. In this work, we identify such uncertainty miscalibration problems in a probabilistic LiDAR 3D object detection network, and propose three practical methods to significantly reduce errors in uncertainty calibration. Extensive experiments on several datasets show that our met…
Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability to tailor such strategies to inoculate a model against specific classes of corruptions or attacks -- without incurring substantial losses in robustness against other classes of corruptions -- remains elusive. In this work, we successfully harden a model against Fourier-based attacks, while producing superior-to-AugMix accuracy and calibration results on both the CIFAR-10-C and CIFAR-100-C datasets; classification erro…
