Research on Image Out-of-Distribution Detection: A Review

被引：0
|
作者：
Guo L. [1 ,2 ,3 ]
Li G. [1 ,2 ]
Gong K. [1 ,2 ]
Xue Z. [3 ]
机构：
[1] College of Information Science and Engineering, China University of Petroleum, Beijing
[2] Beijing Key Laboratory of Petroleum Data Mining, China University of Petroleum, Beijing
[3] College of Computer and Information Engineering, Henan Normal University, Xinxiang
来源：
Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2023年 / 36卷 / 07期
关键词：
Deep Learning; Image Recognition; Machine Learning; Out-of-Distribution(OOD) Detection;
D O I：
10.16451/j.cnki.issn1003-6059.202307004
中图分类号：
学科分类号：
摘要：
Classifier learning assumes that the training data and the testing data are independent and identically distributed. Due to the overly stringent assumption, erroneous sample recognition of classifiers for out-of-distribution examples is often caused. Therefore, thorough research on out-of-distribution (OOD) detection becomes paramount. Firstly, the definition of OOD detection and the relevant research are introduced. A comprehensive overview of supervised detection methods, semi-supervised detection methods, unsupervised detection methods and outlier exposure detection methods is provided according to the difference of network training methods. Then, the existing OOD detection methods are summarized from the aspect of three key technologies: neural network classifiers, metric learning and deep generative models. Finally, research trends of OOD detection are discussed. © 2023 Journal of Pattern Recognition and Artificial Intelligence. All rights reserved.
引用
收藏
页码：613 / 633
页数：20
相关论文
共 124 条
  • [1] GOODFELLOW I J, SHLENS J, SZEGEDY C., Explaining and Harnessing Adversarial Examples
  • [2] HENDRYCKS D, GIMPEL K., A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
  • [3] YU C, ZHU X Y, LEI Z, Et al., Out-of-Distribution Detection for Reliable Face Recognition, IEEE Signal Processing Letters, 27, pp. 710-714, (2020)
  • [4] BOYER P, BURNS D, WHYNE C., Out-of-Distribution Detection of Human Activity Recognition with Smartwatch Inertial Sensors, Sensors, 21, 5, (2021)
  • [5] MARTENSSON G, FERREIRA D, GRANBERG T, Et al., The Reliability of a Deep Learning Model in Clinical Out-of-Distribution MRI Data: A Multicohort Study, Medical Image Analysis, 66, (2020)
  • [6] GAO L, WU S D., Response Score of Deep Learning for Out-of-Distribution Sample Detection of Medical Images, Journal of Biomedical Informatics, (2020)
  • [7] DE ANGELI K, GAO S, DANCIU I, Et al., Class Imbalance in Out-of-Distribution Datasets: Improving the Robustness of the TextCNN for the Classification of Rare Cancer Types, Journal of Biomedical Informatics, 125, (2022)
  • [8] REN J, LIU P J, FERTIG E, Et al., Likelihood Ratios for Out-of-Distribution Detection, Proc of the 33rd International Conference on Neural Information Processing Systems, pp. 14707-14718, (2019)
  • [9] MOHSENI M, YAP J, YOLLAND W, Et al., Out-of-Distribution Detection for Dermoscopic Image Classification
  • [10] CAI F Y, KOUTSOUKOS X., Real-Time Out-of-Distribution Detection in Learning-Enabled Cyber-Physical Systems, Proc of the ACM/IEEE 11th International Conference on Cyber-Physical Systems, pp. 174-183, (2020)
12345678910