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

[41] Robust Cough Detection With Out-of-Distribution Detection
Chen, Yuhan
Attri, Pankaj
Barahona, Jeffrey
Hernandez, Michelle L.
Carpenter, Delesha
Bozkurt, Alper
Lobaton, Edgar
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (07) : 3210 - 3221
[42] Exploring the Limits of Out-of-Distribution Detection
Fort, Stanislav
Ren, Jie
Lakshminarayanan, Balaji
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[43] On Risk Assessment for Out-of-Distribution Detection
Vasiliuk, Anton
IEEE ACCESS, 2025, 13 : 18546 - 18568
[44] Semantic enhanced for out-of-distribution detection
Jiang, Weijie
Yu, Yuanlong
FRONTIERS IN NEUROROBOTICS, 2022, 16
[45] Likelihood Ratios for Out-of-Distribution Detection
Ren, Jie
Liu, Peter J.
Fertig, Emily
Snoek, Jasper
Poplin, Ryan
DePristo, Mark A.
Dillon, Joshua V.
Lakshminarayanan, Balaji
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[46] Semantically Coherent Out-of-Distribution Detection
Yang, Jingkang
Wang, Haoqi
Feng, Litong
Yan, Xiaopeng
Zheng, Huabin
Zhang, Wayne
Liub, Ziwei
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 8281 - 8289
[47] Generalized Out-of-Distribution Detection: A Survey
Yang, Jingkang
Zhou, Kaiyang
Li, Yixuan
Liu, Ziwei
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, 132 (12) : 5635 - 5662
[48] Unsupervised evaluation for out-of-distribution detection
Zhang, Yuhang
Hu, Jiani
Wen, Dongchao
Deng, Weihong
PATTERN RECOGNITION, 2025, 160
[49] Inductive Conformal Out-of-distribution Detection based on Adversarial Autoencoders
Cai, Feiyang
Ozdagli, Ali, I
Potteiger, Nicholas
Koutsoukos, Xenofon
2021 IEEE INTERNATIONAL CONFERENCE ON OMNI-LAYER INTELLIGENT SYSTEMS (IEEE COINS 2021), 2021, : 90 - 95
[50] Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection
Zhou, Yibo
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 7369 - 7377

← 1 2 3 4 5 →