The vast majority of uncertainty quantification methods for deep object detectors such as variational inference are based on the network output. Here, we study gradient-based epistemic uncertainty metrics for deep object detectors to obtain reliable confidence estimates. We show that they contain predictive information and that they capture information orthogonal to that of common, output-based uncertainty estimation methods like Monte-Carlo dropout and deep ensembles. To this end, we use meta classification and meta regression to produce confidence estimates using gradient metrics and other baselines for uncertainty quantification which are in principle applicable to any object detection architecture. Specifically, we employ false positive detection and prediction of localization quality to investigate uncertainty content of our metrics and compute the calibration errors of meta classifiers. Moreover, we use them as a post-processing filter mechanism to the object detection pipeline and compare object detection performance. Our results show that gradient-based uncertainty is itself on par with output-based methods across different detectors and datasets. More significantly, combined meta classifiers based on gradient and output-based metrics outperform the standalone models. Based on this result, we conclude that gradient uncertainty adds orthogonal information to output-based methods. This suggests that variational inference may be supplemented by gradient-based uncertainty to obtain improved confidence measures, contributing to down-stream applications of deep object detectors and improving their probabilistic reliability.
ETH Zurich（苏黎世联邦理工学院）；Technical University Munich（慕尼黑工业大学）；Google（谷歌）
A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution (OOD) data while adding negligible computational costs at inference time. However, it remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications - both prerequisites for their practical deployment. To this end, we fir…
There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining…
German Research Center for Artificial Intelligence（德国人工智能研究中心）
Uncertainty quantification in neural network promises to increase safety of AI systems, but it is not clear how performance might vary with the training set size. In this paper we evaluate seven uncertainty methods on Fashion MNIST and CIFAR10, as we sub-sample and produce varied training set sizes. We find that calibration error and out of distribution detection performance strongly depend on the training set size, with most methods being miscalibrated on the test set with small training sets. Gradient-based methods seem to poorly estimate epistemic uncertainty and are the most affected by tr…
In this paper, we introduce a Bayesian deep learning based model for segmenting the photoreceptor layer in pathological OCT scans. Our architecture provides accurate segmentations of the photoreceptor layer and produces pixel-wise epistemic uncertainty maps that highlight potential areas of pathologies or segmentation errors. We empirically evaluated this approach in two sets of pathological OCT scans of patients with age-related macular degeneration, retinal vein oclussion and diabetic macular edema, improving the performance of the baseline U-Net both in terms of the Dice index and the area …
University of Groningen（格罗宁根大学）；Pontifical Catholic University of Peru（秘鲁天主大学）
Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, som…
Epistemic Uncertainty for Generated Image Detection
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（脑启发智能感知与认知联合实验室，中国科学技术大学）；Hong Kong Baptist University（香港 Baptist 大学）；Sydney AI Centre, The University of Sydney（悉尼人工智能中心，悉尼大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. While novel denoising networks were designed for real images coming from different distributions, or for specific applications, comparatively small improvement was achieved on Gaussian denoising. The denoising solutions suffer from epistemic uncertainty that can limit further advancements. This uncertainty is traditionally mitigated through different ensemble approaches. However, such ensembles are prohibitively costly with deep networks, which ar…
Hamburg University of Technology（汉堡工业大学）；Leibniz Universität Hannover（莱布尼茨汉诺威大学）；Hannover Medical School（汉诺威医学院）；The Hospital for Sick Children（多伦多病童医院）；University of Toronto Mississauga（多伦多大学密西沙加校区）
The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carlo dropout to regression tasks and show that predictive uncertainty is systematically underestimated. We apply $ σ$ scaling with a single scalar value; a simple, yet effective calibration method for both types of uncertainty. The performance of our approach is evaluated on a variety of common medical regression data sets using different state-of-the-art convolutional network arc…
A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentation
Erasmus MC（伊拉斯姆斯医学中心）；University Medical Center Utrecht（乌得勒支大学医学中心）；Academic Medical Center University of Amsterdam（阿姆斯特丹大学学术医学中心）；Maastricht University Medical Center（马斯特里赫特大学医学中心）；University of Copenhagen（哥本哈根大学）
Age-related macular degeneration (AMD) is one of the leading causes of permanent vision loss in people aged over 60 years. Accurate segmentation of biomarkers such as drusen that points to the early stages of AMD is crucial in preventing further vision impairment. However, segmenting drusen is extremely challenging due to their varied sizes and appearances, low contrast and noise resemblance. Most existing literature, therefore, have focused on size estimation of drusen using classification, leaving the challenge of accurate segmentation less tackled. Additionally, obtaining the pixel-wise ann…
Graz University of Technology（格拉茨技术大学）；Silicon Austria Labs（奥地利硅谷实验室）；University of Bonn（波恩大学）；Johannes Kepler University（约翰·开普勒大学）；Technical University of Munich（慕尼黑工业大学）；Imperial College London（伦敦帝国理工学院）；NYU School of Medicine（纽约大学医学院）
Recent deep learning approaches focus on improving quantitative scores of dedicated benchmarks, and therefore only reduce the observation-related (aleatoric) uncertainty. However, the model-immanent (epistemic) uncertainty is less frequently systematically analyzed. In this work, we introduce a Bayesian variational framework to quantify the epistemic uncertainty. To this end, we solve the linear inverse problem of undersampled MRI reconstruction in a variational setting. The associated energy functional is composed of a data fidelity term and the total deep variation (TDV) as a learned paramet…
