v1v2 (latest)

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 (abs)PDF HTML

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

50 / 366 papers shown

Title
Are DNNs fooled by extremely unrecognizable images? Soichiro Kumano Hiroshi Kera T. Yamasaki AAML 196 3 0 07 Dec 2020
Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery WorkflowsACS Omega (ACS Omega), 2020 Jize Zhang B. Kailkhura T. Y. Han OOD 127 20 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 253 73 0 30 Nov 2020
Probing Predictions on OOD Images via Nearest Categories Yao-Yuan Yang Cyrus Rashtchian Ruslan Salakhutdinov Kamalika Chaudhuri AAML 366 0 0 17 Nov 2020
Detecting Early Onset of Depression from Social Media Text using Learned Confidence Scores Ana-Maria Bucur Liviu P. Dinu 57 15 0 03 Nov 2020
Learning Open Set Network with Discriminative Reciprocal PointsEuropean Conference on Computer Vision (ECCV), 2020 Guangyao Chen Limeng Qiao Yemin Shi Peixi Peng Jia Li Tiejun Huang Shiliang Pu Yonghong Tian UQCV EDL 225 234 0 31 Oct 2020
PAL : Pretext-based Active LearningBritish Machine Vision Conference (BMVC), 2020 Shubhang Bhatnagar Sachin Goyal Darshan Tank A. Sethi 135 12 0 29 Oct 2020
Classification with Rejection Based on Cost-sensitive Classification Nontawat Charoenphakdee Zhenghang Cui Yivan Zhang Masashi Sugiyama 439 73 0 22 Oct 2020
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution ExamplesNeural Information Processing Systems (NeurIPS), 2020 Jay Nandy Wynne Hsu Yang Deng UQCV 223 68 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 691 808 0 19 Oct 2020
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial RobustnessProceedings of the IEEE (Proc. IEEE), 2020 Guillermo Ortiz-Jiménez Apostolos Modas Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 328 50 0 19 Oct 2020
Stationary Activations for Uncertainty Calibration in Deep LearningNeural Information Processing Systems (NeurIPS), 2020 Lassi Meronen Christabella Irwanto Arno Solin UQCV BDL 136 20 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 180 16 0 14 Oct 2020
Energy-based Out-of-distribution Detection Weitang Liu Xiaoyun Wang John Douglas Owens Shouqing Yang OODD 951 1,643 0 08 Oct 2020
Learnable Uncertainty under Laplace Approximations Agustinus Kristiadi Matthias Hein Philipp Hennig UQCV BDL 195 39 0 06 Oct 2020
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence Agustinus Kristiadi Matthias Hein Philipp Hennig BDL 213 9 0 06 Oct 2020
MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority MapsInternational Conference on Pattern Recognition Applications and Methods (ICPRAM), 2020 Pascal Colling L. Roese-Koerner Hanno Gottschalk Matthias Rottmann 107 27 0 05 Oct 2020
How Neural Networks Extrapolate: From Feedforward to Graph Neural NetworksInternational Conference on Learning Representations (ICLR), 2020 Keyulu Xu Mozhi Zhang Jingling Li S. Du Ken-ichi Kawarabayashi Stefanie Jegelka MLT 663 345 0 24 Sep 2020
Detection of Iterative Adversarial Attacks via Counter AttackJournal of Optimization Theory and Applications (JOTA), 2020 Matthias Rottmann Kira Maag Mathis Peyron N. Krejić Hanno Gottschalk AAML 169 5 0 23 Sep 2020
Regularizing Attention Networks for Anomaly Detection in Visual Question AnsweringAAAI Conference on Artificial Intelligence (AAAI), 2020 Doyup Lee Yeongjae Cheon Wook-Shin Han AAML OOD 189 16 0 21 Sep 2020
Adaptive Label Smoothing Ujwal Krothapalli A. Lynn Abbott 187 11 0 14 Sep 2020
A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples Julia Lust Alexandru Paul Condurache UQCV AAML AI4CE 182 8 0 21 Aug 2020
A General Framework For Detecting Anomalous Inputs to DNN ClassifiersInternational Conference on Machine Learning (ICML), 2020 Jayaram Raghuram Varun Chandrasekaran S. Jha Suman Banerjee AAML 227 38 0 29 Jul 2020
Certifiably Adversarially Robust Detection of Out-of-Distribution Data Julian Bitterwolf Alexander Meinke Matthias Hein 328 9 0 16 Jul 2020
Nested Learning For Multi-Granular Tasks Raphaël Achddou J. Matias Di Martino Guillermo Sapiro 125 1 0 13 Jul 2020
Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks Shreyas Padhy Zachary Nado Jie Jessie Ren J. Liu Jasper Snoek Balaji Lakshminarayanan UQCV 223 48 0 10 Jul 2020
Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks Doyup Lee Yeongjae Cheon 89 6 0 07 Jul 2020
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining Jiefeng Chen Shouqing Yang Xi Wu Yingyu Liang S. Jha OODD 311 164 0 26 Jun 2020
Hyperparameter Ensembles for Robustness and Uncertainty QuantificationNeural Information Processing Systems (NeurIPS), 2020 F. Wenzel Jasper Snoek Dustin Tran Rodolphe Jenatton UQCV 453 233 0 24 Jun 2020
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness Jeremiah Zhe Liu Zi Lin Shreyas Padhy Dustin Tran Tania Bedrax-Weiss Balaji Lakshminarayanan UQCV BDL 747 514 0 17 Jun 2020
Revisiting Explicit Regularization in Neural Networks for Well-Calibrated Predictive Uncertainty Taejong Joo U. Chung BDL UQCV 218 0 0 11 Jun 2020
A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers Niccolò Antonello Philip N. Garner 177 4 0 09 Jun 2020
Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples David Macêdo T. I. Ren Cleber Zanchettin Adriano Oliveira Teresa B Ludermir OODD 168 27 0 07 Jun 2020
Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers S. Melacci Gabriele Ciravegna Angelo Sotgiu Ambra Demontis Battista Biggio Marco Gori Fabio Roli 227 18 0 06 Jun 2020
ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy Natalia Shepeleva Werner Zellinger Michal Lewandowski Bernhard A. Moser 110 3 0 20 May 2020
A Review of Computer Vision Methods in Network Security Jiawei Zhao Rahat Masood Suranga Seneviratne AAML 133 52 0 07 May 2020
Shortcut Learning in Deep Neural NetworksNature Machine Intelligence (NMI), 2020 Robert Geirhos J. Jacobsen Claudio Michaelis R. Zemel Wieland Brendel Matthias Bethge Felix Wichmann 902 2,404 0 16 Apr 2020
Robust Out-of-distribution Detection for Neural Networks Jiefeng Chen Shouqing Yang Xi Wu Yingyu Liang S. Jha OODD 484 98 0 21 Mar 2020
Adversarial Robustness on In- and Out-Distribution Improves ExplainabilityEuropean Conference on Computer Vision (ECCV), 2020 Maximilian Augustin Alexander Meinke Matthias Hein OOD 310 107 0 20 Mar 2020
Synthesize then Compare: Detecting Failures and Anomalies for Semantic SegmentationEuropean Conference on Computer Vision (ECCV), 2020 Yingda Xia Yi Zhang Fengze Liu Wei Shen Alan Yuille UQCV 256 161 0 18 Mar 2020
Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep LearningInternational Conference on Machine Learning (ICML), 2020 Jize Zhang B. Kailkhura T. Y. Han UQCV 276 255 0 16 Mar 2020
No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial AttacksIEEE Transactions on Medical Imaging (TMI), 2020 Siqi Liu A. Setio Florin-Cristian Ghesu Eli Gibson Sasa Grbic Bogdan Georgescu Dorin Comaniciu AAML OOD 294 44 0 08 Mar 2020
Dropout Strikes Back: Improved Uncertainty Estimation via Diversity SamplingInternational Joint Conference on the Analysis of Images, Social Networks and Texts (AISNT), 2020 Kirill Fedyanin Evgenii Tsymbalov Maxim Panov UQCV 160 7 0 06 Mar 2020
Fast Predictive Uncertainty for Classification with Bayesian Deep NetworksConference on Uncertainty in Artificial Intelligence (UAI), 2020 Marius Hobbhahn Agustinus Kristiadi Philipp Hennig BDL UQCV 410 39 0 02 Mar 2020
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU NetworksInternational Conference on Machine Learning (ICML), 2020 Agustinus Kristiadi Matthias Hein Philipp Hennig BDL UQCV 319 322 0 24 Feb 2020
On the Role of Dataset Quality and Heterogeneity in Model Confidence Yuan Zhao Jiasi Chen Samet Oymak 74 15 0 23 Feb 2020
On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation N. Brosse C. Riquelme Alice Martin Sylvain Gelly Eric Moulines BDL OOD UQCV 153 36 0 22 Jan 2020
Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Tasks Oliver Willers Sebastian Sudholt Shervin Raafatnia Stephanie Abrecht 207 82 0 22 Jan 2020
Safe Robot Navigation via Multi-Modal Anomaly DetectionIEEE Robotics and Automation Letters (RA-L), 2020 Lorenz Wellhausen René Ranftl Marco Hutter 182 83 0 22 Jan 2020
Practical Solutions for Machine Learning Safety in Autonomous Vehicles Sina Mohseni Mandar Pitale Vasu Singh Zinan Lin 156 71 0 20 Dec 2019