We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn better representations, but also permits building one-class classifiers that are faithful to the target task. We argue that classifiers inspired by the statistical perspective in generative or discriminative models are more effective than existing approaches, such as a normality score from a surrogate classifier. We thoroughly evaluate different self-supervised representation learning algorithms under the proposed framework for one-class classification. Moreover, we present a novel distribution-augmented contrastive learning that extends training distributions via data augmentation to obstruct the uniformity of contrastive representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks, including novelty and anomaly detection. Finally, we present visual explanations, confirming that the decision-making process of deep one-class classifiers is intuitive to humans. The code is available at https://github.com/google-research/deep_representation_one_class.
VWise: A novel benchmark for evaluating scene classification for vehicular applications
Voxar Labs(沃克斯实验室);Centro de Informática(信息中心);Universidade Federal de Pernambuco(伯南布哥联邦大学);Departamento de Eletrônica e Sistemas(电子与系统系);Volkswagen Trucks and Bus(大众卡车与巴士公司)
Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
Department of Computer Engineering Benedict College Columbia, SC, USA(计算机工程系 布恩迪克学院 美国哥伦比亚州);Department of Computer Science Benedict College Columbia, SC, USA(计算机科学系 布恩迪克学院 美国哥伦比亚州);Department of Civil Engineering Clemson University Clemson, SC, USA(土木工程系 哥伦比亚大学 美国哥伦布州)
Evaluating Data Augmentation Techniques for Coffee Leaf Disease Classification
National University of Science and Technology POLITEHNICA Bucharest(布加勒斯特理工国立科学技术大学);National Institute for Research and Development in Informatics - ICI Bucharest(布加勒斯特国家信息学研发研究所(ICI布加勒斯特));Academy of Romanian Scientists(罗马尼亚科学家学院)
Evaluating Vision Foundation Models for Pixel and Object Classification in Microscopy
Georg-August-University Göttingen, Institute of Computer Science Department of Tissue Dynamics;Regeneration, Max Planck Institute for Multidisciplinary Sciences, Göttingen Georg-August-University Göttingen, Faculty of Biology;Psychology CAIMed - Lower Saxony Center for AI \& Causal Methods in Medicine, Göttingen Cluster of Excellence Multiscale Bioimaging (MBExC), Georg-August-University Göttingen
Evaluating the visualization of what a Deep Neural Network has learned
Fraunhofer Heinrich Hertz Institute(弗劳恩霍夫海因里希·赫兹研究所);Singapore University of Technology and Design (SUTD)(新加坡科技设计大学);Berlin Institute of Technology (TU Berlin)(柏林工业大学);Korea University(高丽大学)
Evaluating 35 Methods to Generate Structural Connectomes Using Pairwise Classification
University of Southern California(南加州大学);The Institute for Information Transmission Problems(信息传输问题研究所);Skoltech Institute of Science and Technology(斯科尔科沃科学技术学院);Indiana University(印第安纳大学)
Deep Learning in Image Classification: Evaluating VGG19's Performance on Complex Visual Data
University of California, Los Angeles(加州大学洛杉矶分校);Rice University(莱斯大学);University of Houston(休斯顿大学);University of Pennsylvania(宾夕法尼亚大学);Tulane University(杜兰大学);Johns Hopkins University(约翰斯·霍普金斯大学)
Evaluating Synthetic Images as Effective Substitutes for Experimental Data in Surface Roughness Classification
State Key Laboratory of Ultra-precision Machining Technology, Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University(香港理工大学工业及系统工程学系超精密加工技术国家重点实验室);Division of Science, Engineering and Health Studies, The School of Professional Education and Executive Development, The Hong Kong Polytechnic University(香港理工大学专业进修学院科学、工程及健康研究学部);Department of Science and Environmental Studies, The Education University of Hong Kong(香港教育大学科学与环境研究学系)
Screening Autism Spectrum Disorder in children using Deep Learning Approach : Evaluating the classification model of YOLOv26s by comparing with other models
Coventry University(考文垂大学);University of Memphis(孟菲斯大学);University of Massachusetts Boston(马萨诸塞大学波士顿分校);University of Nevada Las vegas(内华达大学拉斯维加斯分校);Softwarica College(索夫瓦里卡学院);GEICO(盖可保险公司);Growphase Technology(格罗法斯科技);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Curry College(库里学院)
Evaluating Single and Multi-Omics Based Explainable Artificial Intelligence (MOXAI) for Molecular Subclass Classification of Adult-Type Diffuse Gliomas
Evaluating Deep Learning-based Melanoma Classification using Immunohistochemistry and Routine Histology: A Three Center Study
German Cancer Research Center (DKFZ)(德国癌症研究中心(DKFZ));University Heidelberg(海德堡大学);Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden(德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯医学院与大学医院);Istituto Nazionale Tumori di Napoli, IRCCS “G. Pascale”(那不勒斯国家肿瘤研究所IRCCS“G.帕斯卡莱”)
Evaluating the Transferability and Adversarial Discrimination of Convolutional Neural Networks for Threat Object Detection and Classification within X-Ray Security Imagery
Evaluating LeNet Algorithms in Classification Lung Cancer from Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases
Faculty of Electrical and Computer Engineering, Islamic Azad University(伊斯兰阿扎德大学电气与计算机工程学院);Young Researchers and Elite Club, Ardabil Branch, Islamic Azad University(伊斯兰阿扎德大学阿尔达比尔分校青年研究者与精英俱乐部);Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases(伊拉克肿瘤学教学医院/国家癌症疾病中心)