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
Monitoring and Adapting ML Models on Mobile Devices Wei Hao Zixi Wang Lauren Hong Lingxi Li Nader Karayanni Chengzhi Mao Junfeng Yang Asaf Cidon OffRL 22 4 0 12 May 2023
Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement Ailin Deng Miao Xiong Bryan Hooi 38 6 0 02 May 2023
Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization Agustinus Kristiadi Alexander Immer Runa Eschenhagen Vincent Fortuin BDL UQCV 15 8 0 17 Apr 2023
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction Jiefeng Chen Jinsung Yoon Sayna Ebrahimi Sercan Ö. Arik S. Jha Tomas Pfister 30 1 0 07 Apr 2023
Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection Nicola Franco Daniel Korth J. Lorenz Karsten Roscher Stephan Guennemann 28 5 0 27 Mar 2023
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection Jingyang Zhang Nathan Inkawhich Randolph Linderman R. Luley Yiran Chen H. Li OODD 16 1 0 25 Mar 2023
Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection Muhammad Akhtar Munir Muhammad Haris Khan Salman Khan F. Khan UQCV 32 15 0 25 Mar 2023
ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning Islam Nassar Munawar Hayat Ehsan Abbasnejad Hamid Rezatofighi Gholamreza Haffari 32 17 0 22 Mar 2023
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models Tong Ye Shijing Si Jianzong Wang Ning Cheng Zhitao Li Jing Xiao 69 2 0 15 Mar 2023
InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning Z. Yu Yin Li Yong Jae Lee 24 10 0 13 Mar 2023
Non-Parametric Outlier Synthesis Leitian Tao Xuefeng Du Xiaojin Zhu Yixuan Li OODD 17 98 0 06 Mar 2023
DeepLens: Interactive Out-of-distribution Data Detection in NLP Models D. Song Zhijie Wang Yuheng Huang Lei Ma Tianyi Zhang 24 4 0 02 Mar 2023
Uncertainty Injection: A Deep Learning Method for Robust Optimization W. Cui Wei Yu UQCV OOD 14 6 0 23 Feb 2023
VRA: Variational Rectified Activation for Out-of-distribution Detection Ming Xu Zheng Lian B. Liu Jianhua Tao OODD 19 7 0 23 Feb 2023
Fixing Overconfidence in Dynamic Neural Networks Lassi Meronen Martin Trapp Andrea Pilzer Le Yang Arno Solin BDL 34 16 0 13 Feb 2023
Learning to Scale Temperature in Masked Self-Attention for Image Inpainting Xiang Zhou Yuan Zeng Yi Gong 32 2 0 13 Feb 2023
Better Diffusion Models Further Improve Adversarial Training Zekai Wang Tianyu Pang Chao Du Min-Bin Lin Weiwei Liu Shuicheng Yan DiffM 24 208 0 09 Feb 2023
Energy-based Out-of-Distribution Detection for Graph Neural Networks Qitian Wu Yiting Chen Chenxiao Yang Junchi Yan OODD 19 57 0 06 Feb 2023
Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness Ailin Deng Shen Li Miao Xiong Zhirui Chen Bryan Hooi 16 4 0 06 Feb 2023
Interpretable Out-Of-Distribution Detection Using Pattern Identification Romain Xu-Darme Julien Girard-Satabin Darryl Hond Gabriele Incorvaia Zakaria Chihani OODD 22 3 0 24 Jan 2023
Key Feature Replacement of In-Distribution Samples for Out-of-Distribution Detection Jaeyoung Kim Seo Taek Kong Dongbin Na Kyu-Hwan Jung OODD 16 4 0 26 Dec 2022
Boosting Out-of-Distribution Detection with Multiple Pre-trained Models Feng Xue Zi He Chuanlong Xie Falong Tan Zhenguo Li OODD 30 7 0 24 Dec 2022
Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data Maxime Darrin Pablo Piantanida Pierre Colombo OODD 45 12 0 18 Dec 2022
Improving group robustness under noisy labels using predictive uncertainty Dongpin Oh Dae Lee Jeunghyun Byun Bonggun Shin UQCV 23 3 0 14 Dec 2022
Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet Yannic Neuhaus Maximilian Augustin Valentyn Boreiko Matthias Hein AAML 36 30 0 09 Dec 2022
Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation Ibrahim Batuhan Akkaya U. Halici TTA 18 2 0 08 Dec 2022
Block Selection Method for Using Feature Norm in Out-of-distribution Detection Yeonguk Yu Sungho Shin Seongju Lee C. Jun Kyoobin Lee OODD 17 30 0 05 Dec 2022
Rethinking Out-of-Distribution Detection From a Human-Centric Perspective Yao Zhu YueFeng Chen Xiaodan Li Rong Zhang Hui Xue Xiang Tian Rongxin Jiang Bo Zheng Yao-wu Chen OODD 27 7 0 30 Nov 2022
RbA: Segmenting Unknown Regions Rejected by All Nazir Nayal Mısra Yavuz João F. Henriques Fatma Guney UQCV 19 46 0 25 Nov 2022
Delving into Out-of-Distribution Detection with Vision-Language Representations Yifei Ming Ziyan Cai Jiuxiang Gu Yiyou Sun W. Li Yixuan Li VLM OODD 40 157 0 24 Nov 2022
Promises and Pitfalls of Threshold-based Auto-labeling Harit Vishwakarma Heguang Lin Frederic Sala Ramya Korlakai Vinayak 26 9 0 22 Nov 2022
Are we certain it's anomalous? Alessandro Flaborea Bardh Prenkaj Bharti Munjal Marco Aurelio Sterpa Dario Aragona L. Podo Fabio Galasso 19 8 0 16 Nov 2022
Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS Rishabh Singh José C. Príncipe UQCV 28 3 0 03 Nov 2022
Watermarking for Out-of-distribution Detection Qizhou Wang Feng Liu Yonggang Zhang Jing Zhang Chen Gong Tongliang Liu Bo Han OODD 22 31 0 27 Oct 2022
On double-descent in uncertainty quantification in overparametrized models Lucas Clarté Bruno Loureiro Florent Krzakala Lenka Zdeborová UQCV 39 12 0 23 Oct 2022
Augmentation by Counterfactual Explanation -- Fixing an Overconfident Classifier Sumedha Singla Nihal Murali Forough Arabshahi Sofia Triantafyllou Kayhan Batmanghelich CML 49 4 0 21 Oct 2022
Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity Dennis Ulmer J. Frellsen Christian Hardmeier 185 22 0 20 Oct 2022
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble Hyunsoo Cho Choonghyun Park Jaewoo Kang Kang Min Yoo Taeuk Kim Sang-goo Lee OODD 22 8 0 20 Oct 2022
Packed-Ensembles for Efficient Uncertainty Estimation Olivier Laurent Adrien Lafage Enzo Tartaglione Geoffrey Daniel Jean-Marc Martinez Andrei Bursuc Gianni Franchi OODD 44 32 0 17 Oct 2022
Prediction Calibration for Generalized Few-shot Semantic Segmentation Zhihe Lu Sen He Da Li Yi-Zhe Song Tao Xiang ViT 27 22 0 15 Oct 2022
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection Jingkang Yang Pengyun Wang Dejian Zou Zitang Zhou Kun Ding ... Kaiyang Zhou Wayne Zhang Dan Hendrycks Yixuan Li Ziwei Liu OODD 28 225 0 13 Oct 2022
Robust Models are less Over-Confident Julia Grabinski Paul Gavrikov J. Keuper M. Keuper AAML 28 24 0 12 Oct 2022
Curved Representation Space of Vision Transformers Juyeop Kim Junha Park Songkuk Kim Jongseok Lee ViT 33 6 0 11 Oct 2022
Boosting Out-of-distribution Detection with Typical Features Yao Zhu YueFeng Chen Chuanlong Xie Xiaodan Li Rong Zhang Hui Xue Xiang Tian Bolun Zheng Yao-wu Chen OODD 78 50 0 09 Oct 2022
To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer Models Julius Gonsior C. Falkenberg Silvio Magino Anja Reusch Maik Thiele Wolfgang Lehner UQCV 36 7 0 06 Oct 2022
Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects Kira Maag Robin Shing Moon Chan Svenja Uhlemeyer K. Kowol Hanno Gottschalk 32 19 0 05 Oct 2022
On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks Huimin Zeng Zhenrui Yue Yang Zhang Ziyi Kou Lanyu Shang Dong Wang OOD AAML 33 7 0 03 Oct 2022
Your Out-of-Distribution Detection Method is Not Robust! Mohammad Azizmalayeri Arshia Soltani Moakhar Arman Zarei Reihaneh Zohrabi M. T. Manzuri M. Rohban OODD 35 15 0 30 Sep 2022
Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization Jingyang Lin Yu Wang Qi Cai Yingwei Pan Ting Yao Hongyang Chao Tao Mei OODD 26 3 0 26 Sep 2022
Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks J. Haas William Yolland B. Rabus OODD 41 14 0 17 Sep 2022