Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem

13 December 2018

Matthias Hein

Maksym Andriushchenko

Julian Bitterwolf

OODD

ArXiv PDF HTML

Papers citing "Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem"

50 / 349 papers shown

Title
Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra Kanil Patel William H. Beluch K. Rambach Adriana-Eliza Cozma Michael Pfeiffer Bin Yang EDL UQCV 16 5 0 01 Jun 2021
Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle J. Woo 34 11 0 30 May 2021
Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss David Macêdo Teresa B Ludermir OODD 21 12 0 30 May 2021
DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling Akis Linardos Matthias Kümmerer Ori Press Matthias Bethge MDE 21 65 0 26 May 2021
Masked Contrastive Learning for Anomaly Detection Hyunsoo Cho Jinseok Seol Sang-goo Lee SSL 11 41 0 18 May 2021
Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions Bertrand Charpentier Oliver Borchert Daniel Zügner Simon Geisler Stephan Günnemann UQCV BDL 22 17 0 10 May 2021
Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs Théo Lacombe Yuichi Ike Mathieu Carrière Frédéric Chazal Marc Glisse Yuhei Umeda 13 20 0 07 May 2021
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space Rui Huang Yixuan Li OODD 33 235 0 05 May 2021
SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation Robin Shing Moon Chan Krzysztof Lis Svenja Uhlemeyer Hermann Blum S. Honari Roland Siegwart Pascal Fua Mathieu Salzmann Matthias Rottmann UQCV 21 136 0 30 Apr 2021
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety Sebastian Houben Stephanie Abrecht Maram Akila Andreas Bär Felix Brockherde ... Serin Varghese Michael Weber Sebastian J. Wirkert Tim Wirtz Matthias Woehrle AAML 13 58 0 29 Apr 2021
Unsupervised Learning of Multi-level Structures for Anomaly Detection Songmin Dai Jide Li Lu Wang Congcong Zhu Yifan Wu Xiaoqiang Li 15 0 0 25 Apr 2021
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection Xin Dong Junfeng Guo Ang Li W. Ting Cong Liu H. T. Kung OODD 13 57 0 23 Apr 2021
Uncertainty Surrogates for Deep Learning R. Achanta Natasa Tagasovska OOD UQCV 19 0 0 16 Apr 2021
Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey Thomas Rojat Raphael Puget David Filliat Javier Del Ser R. Gelin Natalia Díaz Rodríguez XAI AI4TS 36 127 0 02 Apr 2021
The Compact Support Neural Network Adrian Barbu Hongyu Mou 11 5 0 01 Apr 2021
Learning Placeholders for Open-Set Recognition Da-Wei Zhou Han-Jia Ye De-Chuan Zhan VLM 6 194 0 28 Mar 2021
Posterior Meta-Replay for Continual Learning Christian Henning Maria R. Cervera Francesco DÁngelo J. Oswald Regina Traber Benjamin Ehret Seijin Kobayashi Benjamin Grewe João Sacramento CLL BDL 51 54 0 01 Mar 2021
Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning David S. W. Williams Matthew Gadd D. Martini Paul Newman OODD 11 13 0 01 Mar 2021
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications Leonard Berrada Sumanth Dathathri Krishnamurthy Dvijotham Robert Stanforth Rudy Bunel J. Uesato Sven Gowal M. P. Kumar AAML OOD 30 17 0 18 Feb 2021
Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches Jasmin Breitenstein Jan-Aike Termöhlen Daniel Lipinski Tim Fingscheidt AAML 20 35 0 11 Feb 2021
Dynamic Neural Networks: A Survey Yizeng Han Gao Huang Shiji Song Le Yang Honghui Wang Yulin Wang 3DH AI4TS AI4CE 18 621 0 09 Feb 2021
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization Yivan Zhang Gang Niu Masashi Sugiyama NoLa 28 78 0 04 Feb 2021
One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision Zaid Khan Y. Fu 146 51 0 03 Feb 2021
Removing Undesirable Feature Contributions Using Out-of-Distribution Data Saehyung Lee Changhwa Park Hyungyu Lee Jihun Yi Jonghyun Lee Sungroh Yoon OODD 11 24 0 17 Jan 2021
Spending Your Winning Lottery Better After Drawing It Ajay Jaiswal Haoyu Ma Tianlong Chen Ying Ding Zhangyang Wang 15 6 0 08 Jan 2021
Multidimensional Uncertainty-Aware Evidential Neural Networks Yibo Hu Yuzhe Ou Xujiang Zhao Jin-Hee Cho Feng Chen EDL UQCV AAML 25 23 0 26 Dec 2020
Out-distribution aware Self-training in an Open World Setting Maximilian Augustin Matthias Hein 17 7 0 21 Dec 2020
Learning Energy-Based Models With Adversarial Training Xuwang Yin Shiying Li Gustavo K. Rohde AAML DiffM 33 9 0 11 Dec 2020
Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detection Dennis Ulmer Giovanni Cina OODD 32 31 0 09 Dec 2020
Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation Robin Shing Moon Chan Matthias Rottmann Hanno Gottschalk OODD 37 149 0 09 Dec 2020
Are DNNs fooled by extremely unrecognizable images? Soichiro Kumano Hiroshi Kera T. Yamasaki AAML 18 2 0 07 Dec 2020
Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery Workflows Jize Zhang B. Kailkhura T. Y. Han OOD 12 13 0 02 Dec 2020
Feature Space Singularity for Out-of-Distribution Detection Haiwen Huang Zhihan Li Lulu Wang Sishuo Chen Bin Dong Xinyu Zhou OODD 20 65 0 30 Nov 2020
Probing Predictions on OOD Images via Nearest Categories Yao-Yuan Yang Cyrus Rashtchian Ruslan Salakhutdinov Kamalika Chaudhuri AAML 25 0 0 17 Nov 2020
Detecting Early Onset of Depression from Social Media Text using Learned Confidence Scores Ana-Maria Bucur Liviu P. Dinu 6 12 0 03 Nov 2020
Learning Open Set Network with Discriminative Reciprocal Points Guangyao Chen Limeng Qiao Yemin Shi Peixi Peng Jia Li Tiejun Huang Shiliang Pu Yonghong Tian UQCV EDL 9 188 0 31 Oct 2020
PAL : Pretext-based Active Learning Shubhang Bhatnagar Sachin Goyal Darshan Tank A. Sethi 11 9 0 29 Oct 2020
Classification with Rejection Based on Cost-sensitive Classification Nontawat Charoenphakdee Zhenghang Cui Yivan Zhang Masashi Sugiyama 68 64 0 22 Oct 2020
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples Jay Nandy W. Hsu M. Lee UQCV 16 60 0 20 Oct 2020
RobustBench: a standardized adversarial robustness benchmark Francesco Croce Maksym Andriushchenko Vikash Sehwag Edoardo Debenedetti Nicolas Flammarion M. Chiang Prateek Mittal Matthias Hein VLM 228 676 0 19 Oct 2020
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness Guillermo Ortiz-Jiménez Apostolos Modas Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 29 48 0 19 Oct 2020
Stationary Activations for Uncertainty Calibration in Deep Learning Lassi Meronen Christabella Irwanto Arno Solin UQCV BDL 6 18 0 19 Oct 2020
Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit Ben Adlam Jaehoon Lee Lechao Xiao Jeffrey Pennington Jasper Snoek UQCV BDL 23 15 0 14 Oct 2020
Energy-based Out-of-distribution Detection Weitang Liu Xiaoyun Wang John Douglas Owens Yixuan Li OODD 62 1,290 0 08 Oct 2020
Learnable Uncertainty under Laplace Approximations Agustinus Kristiadi Matthias Hein Philipp Hennig UQCV BDL 14 30 0 06 Oct 2020
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence Agustinus Kristiadi Matthias Hein Philipp Hennig BDL 15 9 0 06 Oct 2020
MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps Pascal Colling L. Roese-Koerner Hanno Gottschalk Matthias Rottmann 27 26 0 05 Oct 2020
How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks Keyulu Xu Mozhi Zhang Jingling Li S. Du Ken-ichi Kawarabayashi Stefanie Jegelka MLT 13 305 0 24 Sep 2020
Detection of Iterative Adversarial Attacks via Counter Attack Matthias Rottmann Kira Maag Mathis Peyron N. Krejić Hanno Gottschalk AAML 6 4 0 23 Sep 2020
Regularizing Attention Networks for Anomaly Detection in Visual Question Answering Doyup Lee Yeongjae Cheon Wook-Shin Han AAML OOD 8 16 0 21 Sep 2020