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"

49 / 349 papers shown

Title
Adaptive Label Smoothing Ujwal Krothapalli A. Lynn Abbott 33 9 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 A. P. Condurache UQCV AAML AI4CE 29 7 0 21 Aug 2020
A General Framework For Detecting Anomalous Inputs to DNN Classifiers Jayaram Raghuram Varun Chandrasekaran S. Jha Suman Banerjee AAML 28 32 0 29 Jul 2020
Certifiably Adversarially Robust Detection of Out-of-Distribution Data Julian Bitterwolf Alexander Meinke Matthias Hein 10 9 0 16 Jul 2020
Nested Learning For Multi-Granular Tasks Raphaël Achddou J. Matias Di Martino Guillermo Sapiro 19 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 9 45 0 10 Jul 2020
Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks Doyup Lee Yeongjae Cheon 12 6 0 07 Jul 2020
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining Jiefeng Chen Yixuan Li Xi Wu Yingyu Liang S. Jha OODD 24 135 0 26 Jun 2020
Hyperparameter Ensembles for Robustness and Uncertainty Quantification F. Wenzel Jasper Snoek Dustin Tran Rodolphe Jenatton UQCV 33 204 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 37 437 0 17 Jun 2020
Revisiting Explicit Regularization in Neural Networks for Well-Calibrated Predictive Uncertainty Taejong Joo U. Chung BDL UQCV 22 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 26 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 12 22 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 4 14 0 06 Jun 2020
ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy Natalia Shepeleva Werner Zellinger Michal Lewandowski Bernhard A. Moser 22 3 0 20 May 2020
A Review of Computer Vision Methods in Network Security Jiawei Zhao Rahat Masood Suranga Seneviratne AAML 22 47 0 07 May 2020
Shortcut Learning in Deep Neural Networks Robert Geirhos J. Jacobsen Claudio Michaelis R. Zemel Wieland Brendel Matthias Bethge Felix Wichmann 55 1,991 0 16 Apr 2020
Robust Out-of-distribution Detection for Neural Networks Jiefeng Chen Yixuan Li Xi Wu Yingyu Liang S. Jha OODD 161 84 0 21 Mar 2020
Adversarial Robustness on In- and Out-Distribution Improves Explainability Maximilian Augustin Alexander Meinke Matthias Hein OOD 75 99 0 20 Mar 2020
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation Yingda Xia Yi Zhang Fengze Liu Wei Shen Alan Yuille UQCV 19 148 0 18 Mar 2020
Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning Jize Zhang B. Kailkhura T. Y. Han UQCV 30 219 0 16 Mar 2020
No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks Siqi Liu A. Setio Florin-Cristian Ghesu Eli Gibson Sasa Grbic Bogdan Georgescu Dorin Comaniciu AAML OOD 31 40 0 08 Mar 2020
Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling Kirill Fedyanin Evgenii Tsymbalov Maxim Panov UQCV 19 7 0 06 Mar 2020
Fast Predictive Uncertainty for Classification with Bayesian Deep Networks Marius Hobbhahn Agustinus Kristiadi Philipp Hennig BDL UQCV 76 31 0 02 Mar 2020
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks Agustinus Kristiadi Matthias Hein Philipp Hennig BDL UQCV 33 277 0 24 Feb 2020
On the Role of Dataset Quality and Heterogeneity in Model Confidence Yuan Zhao Jiasi Chen Samet Oymak 27 12 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 19 33 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 28 80 0 22 Jan 2020
Safe Robot Navigation via Multi-Modal Anomaly Detection Lorenz Wellhausen René Ranftl Marco Hutter 15 77 0 22 Jan 2020
Practical Solutions for Machine Learning Safety in Autonomous Vehicles Sina Mohseni Mandar Pitale Vasu Singh Zhangyang Wang 30 67 0 20 Dec 2019
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration Kanil Patel William H. Beluch Dan Zhang Michael Pfeiffer Bin Yang UQCV 27 30 0 16 Dec 2019
Playing it Safe: Adversarial Robustness with an Abstain Option Cassidy Laidlaw S. Feizi AAML 31 20 0 25 Nov 2019
Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output Vahdat Abdelzad Krzysztof Czarnecki Rick Salay Taylor Denouden Sachin Vernekar Buu Phan OODD 24 45 0 23 Oct 2019
Toward Metrics for Differentiating Out-of-Distribution Sets Mahdieh Abbasi Changjian Shui Arezoo Rajabi Christian Gagné R. Bobba OODD 28 4 0 18 Oct 2019
Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks David Stutz Matthias Hein Bernt Schiele AAML 19 5 0 14 Oct 2019
Out-of-distribution Detection in Classifiers via Generation Sachin Vernekar Ashish Gaurav Vahdat Abdelzad Taylor Denouden Rick Salay Krzysztof Czarnecki OODD 27 83 0 09 Oct 2019
Towards neural networks that provably know when they don't know Alexander Meinke Matthias Hein OODD 33 139 0 26 Sep 2019
Model-Based and Data-Driven Strategies in Medical Image Computing Daniel Rueckert Julia A. Schnabel OOD MedIm AI4CE 28 50 0 23 Sep 2019
Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations Vishnu Suresh Lokhande Songwong Tasneeyapant Abhay Venkatesh Sathya Ravi Vikas Singh 21 29 0 12 Sep 2019
Entropic Out-of-Distribution Detection David Macêdo T. I. Ren Cleber Zanchettin Adriano Oliveira Teresa B Ludermir OODD UQCV 25 31 0 15 Aug 2019
Interpretable Image Recognition with Hierarchical Prototypes Peter Hase Chaofan Chen Oscar Li Cynthia Rudin VLM 17 110 0 25 Jun 2019
Non-Parametric Calibration for Classification Jonathan Wenger Hedvig Kjellström Rudolph Triebel UQCV 45 79 0 12 Jun 2019
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks Maksym Andriushchenko Matthias Hein 25 61 0 08 Jun 2019
Analysis of Confident-Classifiers for Out-of-distribution Detection Sachin Vernekar Ashish Gaurav Taylor Denouden Buu Phan Vahdat Abdelzad Rick Salay Krzysztof Czarnecki OODD 18 18 0 27 Apr 2019
Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task Kenta Hama Takashi Matsubara K. Uehara Jianfei Cai BDL UQCV 21 6 0 09 Apr 2019
A witness function based construction of discriminative models using Hermite polynomials H. Mhaskar A. Cloninger Xiuyuan Cheng 24 9 0 10 Jan 2019
Disentangling Adversarial Robustness and Generalization David Stutz Matthias Hein Bernt Schiele AAML OOD 194 274 0 03 Dec 2018
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,675 0 05 Dec 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,145 0 06 Jun 2015