Gaussian-Based Runtime Detection of Out-of-distribution Inputs for Neural Networks

被引：5

作者：

Hashemi, Vahid ^{[2
]}

Kretinsky, Jan ^{[1
]}

Mohr, Stefanie ^{[1
]}

Seferis, Emmanouil ^{[1
,2
]}

机构：

[1] Tech Univ Munich, Munich, Germany

[2] AUDI AG, Ettingerstr 60, D-85057 Ingolstadt, Germany

来源：

RUNTIME VERIFICATION (RV 2021) | 2021年 / 12974卷

关键词：

D O I：

10.1007/978-3-030-88494-9_14

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

In this short paper, we introduce a simple approach for run-time monitoring of deep neural networks and show how to use it for out-of-distribution detection. The approach is based on inferring Gaussian models of some of the neurons and layers. Despite its simplicity, it performs better than recently introduced approaches based on interval abstractions which are traditionally used in verification.

引用

页码：254 / 264

页数：11

共 50 条

[11] On the Use of Mahalanobis Distance for Out-of-distribution Detection with Neural Networks for Medical Imaging
Anthony, Harry
Kamnitsas, Konstantinos
UNCERTAINTY FOR SAFE UTILIZATION OF MACHINE LEARNING IN MEDICAL IMAGING, UNSURE 2023, 2023, 14291 : 136 - 146
[12] Convolutional Neural Networks with Compression Complexity Pooling for Out-of-Distribution Image Detection
Yu, Sehun
Lee, Dongha
Yu, Hwanjo
PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2435 - 2441
[13] Generalizing Graph Neural Networks on Out-of-Distribution Graphs
Fan, Shaohua
Wang, Xiao
Shi, Chuan
Cui, Peng
Wang, Bai
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (01) : 322 - 337
[14] SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design
Ben Braiek, Houssem
Tfaily, Ali
Khomh, Foutse
Reid, Thomas
Guida, Ciro
PROCEEDINGS OF THE 37TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING, ASE 2022, 2022,
[15] Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
Zheng, Haotian
Wang, Qizhou
Fang, Zhen
Xia, Xiaobo
Liu, Feng
Liu, Tongliang
Han, Bo
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[16] Neural Mean Discrepancy for Efficient Out-of-Distribution Detection
Dong, Xin
Guo, Junfeng
Li, Ang
Ting, Wei-Te
Liu, Cong
Kung, H. T.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 19195 - 19205
[17] Out-of-Distribution Detection for Deep Neural Networks With Isolation Forest and Local Outlier Factor
Luan, Siyu
Gu, Zonghua
Freidovich, Leonid B.
Jiang, Lili
Zhao, Qingling
IEEE ACCESS, 2021, 9 : 132980 - 132989
[18] Ensemble-Based Out-of-Distribution Detection
Yang, Donghun
Mai Ngoc, Kien
Shin, Iksoo
Lee, Kyong-Ha
Hwang, Myunggwon
ELECTRONICS, 2021, 10 (05) : 1 - 12
[19] Heatmap-based Out-of-Distribution Detection
Hornauer, Julia
Belagiannis, Vasileios
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 2602 - 2611
[20] Rule-Based Out-of-Distribution Detection
De Bernardi G.
Narteni S.
Cambiaso E.
Mongelli M.
IEEE Transactions on Artificial Intelligence, 2024, 5 (06): : 2627 - 2637

← 1 2 3 4 5 →