The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper, we make progress on this problem by training with full label distributions that reflect human perceptual uncertainty. We first present a new benchmark dataset which we call CIFAR10H, containing a full distribution of human labels for each image of the CIFAR10 test set. We then show that, while contemporary classifiers fail to exhibit human-like uncertainty on their own, explicit training on our dataset closes this gap, supports improved generalization to increasingly out-of-training-distribution test datasets, and confers robustness to adversarial attacks.
Uncertainty-aware deep learning methods for robust diabetic retinopathy classification
Department of Computer Science, Aalto University(阿尔托大学计算机科学系);The Alan Turing Institute(艾伦图灵研究所);University of Warwick(华威大学);University College London(伦敦大学学院);Department of Electrical Engineering and Automation, Aalto University(阿尔托大学电气工程与自动化系);Central Finland Health Care District(芬兰中部医疗保健区)
Intra-Class Uncertainty Loss Function for Classification
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心);School of Future Technology, University of Chinese Academy of Sciences(中国科学院大学未来技术学院)
ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification
School of Computing and Artificial Intelligence, Southwest Jiaotong University(计算机与人工智能学院,西南交通大学);Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China(可持续城市智能交通工程研究中心,教育部,成都,中国)
本文提出带逐点不确定性标注的 ModelNet40-E 噪声点云基准,并评估 PointNet、DGCNN 和 Point Transformer v3,表明 Point Transformer v3 校准更优。
Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation
Sichuan University(四川大学);West China Hospital, Sichuan University(四川大学华西医院);Institute of High Performance Computing, Agency for Science, Technology and Research(新加坡科技研究局高性能计算研究所)
Application of Symmetric Uncertainty and Mutual Information to Dimensionality Reduction and Classification of Hyperspectral Images
Mohamed V - Agdal University(穆罕默德五世-阿格达尔大学);Mohamed V - Souissi University(穆罕默德五世-苏伊西大学)
遥感技术是一种获取数据的技术,为有毒物质,必要的构建一个模型知识的应用,如分类。近年来,高光谱图像(HSI)已成为一种高技术工具,其主要目标是对一个区域的点进行分类。HIS是一百多个双向测量,称为波段(或简单的图像),同一区域称为地面真值图(GT)。但有些波段受不同的大气影响而不相关,有些波段含有冗余信息,HSI特征的高维性使得分类精度较低。所有这些波段对于某些应用都很重要;但是对于分类,这些波段中的一小部分是相关的。与HSI相关的问题是降维。许多研究使用互信息(MI)来选择相关波段。其他研究使用MI归一化形式,如对称不确定性,在医学图像应用中。本文介绍了一种同样基于MI的相关波段选择算法,并利用对称不确定系数来控制冗余,提高分类精度。该算法是一种特征选择工具和一种Filter策略。本研究以HSI AVIRIS 92 AV 3C为研究对象。这是一种有效、快速的冗余控制方案。
An uncertainty-aware Bayesian framework for machine learning classification models: A case study in land cover classification
National Physical Laboratory, Teddington, UK(英国国家物理实验室,Teddington);Department of Data Science(数据科学系);Department of Thermal & Radiometric Metrology(热学与辐射计量学系);School of Geography, Geology & the Environment(地理、地质与环境学院)
Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification
School of Electrical Engineering(电气工程学院);Korea Advanced Institute of Science and Technology(韩国科学技术院);Department of Software Convergence(软件融合系);College of Interdisciplinary Studies for Emerging Industries(新兴产业跨学科研究学院);Seoul Women’s University(首尔女子大学)
Structured DropConnect for Uncertainty Inference in Image Classification
Beijing University of Posts and Telecommunications(北京邮电大学);China Mobile Research Institute(中国移动研究院);Beijing Academy of Artificial Intelligence(北京人工智能研究院)
MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification
Birmingham City University(伯明翰城市大学);Assiut University(艾斯尤特大学);Galala University(加拉拉大学);Deakin University(迪肯大学);Ngee Ann Polytechnic(义安理工学院);SUSS University(新加坡社会科学大学);Asia University(亚洲大学)
Expert Uncertainty and Severity Aware Chest X-Ray Classification by Multi-Relationship Graph Learning
University of Texas at Arlington(德克萨斯大学阿灵顿分校);RIKEN(理化学研究所);University of Tokyo(东京大学);National Institute of Health Clinical Center(美国国立卫生研究院临床中心);National Cancer Center Research Institute(国立癌症研究中心研究所)
Technical University of Munich(慕尼黑工业大学);Institute for Automotive Engineering, Munich Institute of Robotics and Machine Intelligence, School of Engineering and Design(汽车工程研究所,慕尼黑机器人与机器智能研究所,工程与设计学院)
Uncertainty-driven ensembles of deep architectures for multiclass classification. Application to COVID-19 diagnosis in chest X-ray images
Elsevier Science Publishers B.V.(爱思唯尔科学出版公司);University of Winchester(温彻斯特大学);Universidad de Granada(格拉纳达大学);Universidad de Malaga(马拉加大学);University of Leicester(莱斯特大学)
Beyond Uncertainty Quantification: Learning Uncertainty for Trust-Informed Neural Network Decisions - A Case Study in COVID-19 Classification
Faculty of Engineering & IT, University of Technology Sydney(技术悉尼大学工程与信息学院);University Research and Innovation Center (EKIK), Óbuda University(奥布达大学研究与创新中心)