Out‐of‐distribution detection based on multi‐classifiers
-
Published:2023-06
Issue:2
Volume:5
Page:95-108
-
ISSN:2517-7567
-
Container-title:Cognitive Computation and Systems
-
language:en
-
Short-container-title:Cognitive Comp and Systems
Author:
Jiang Weijie1ORCID,
Yu Yuanlong1
Affiliation:
1. College of Computer and Data Science/College of Software Fuzhou University Fuzhou China
Abstract
AbstractExisting out‐of‐distribution detection models rely on the prediction of a single classifier and are sensitive to classifier bias, making it difficult to discriminate similar feature out‐of‐distribution data. This article proposed a multi‐classifier‐based model and two strategies to enhance the performance of the model. The model first trains several different base classifiers and obtains the predictions of the test data on each base classifier, then uses cross‐entropy to calculate the dispersion between these predictions, and finally uses the dispersion as a metric to identify the out‐of‐distribution data. A large scatter implies inconsistency in the predictions of the base classifier, and the greater the probability of belonging to the out‐of‐distribution data. The first strategy is applied in the training process of the model to increase the difference between base classifiers by using various scales of Label smoothing regularisation. The second strategy is applied to the inference process of the model by changing the mean and variance of the activations in the neural network to perturb the inference results of the test data. These two strategies can effectively amplify the discrepancy in the dispersion of the in‐distribution and out‐of‐distribution data. The experimental results show that the method in this article can effectively improve the performance of the model in the detection of different types of out‐of‐distribution data, improve the robustness of deep neural networks (DNN) in the face of unknown classes, and promote the application of DNN in systems and engineering with high security requirements.
Funder
National Natural Science Foundation of China
Publisher
Institution of Engineering and Technology (IET)
Subject
Artificial Intelligence,Cognitive Neuroscience,Computer Science Applications,Computer Vision and Pattern Recognition,Experimental and Cognitive Psychology
Reference63 articles.
1. Goodfellow I. Shlens J. Szegedy C.:Explaining and Harnessing Adversarial Examples(2015).https://www.scopus.com/inward/record.uri?eid=2‐s2.0‐85083951001&partnerID=40&md5=b1c942e8e9aae5e0327d278ea41a9327
2. Anomaly detection in traffic using L1-norm minimization extreme learning machine
3. Neural networks for computer-aided diagnosis in medicine: A review
4. Deep Learning for Medical Anomaly Detection – A Survey
5. Hendrycks D. Gimpel K.:A Baseline for Detecting Misclassified and Out‐of‐Distribution Examples in Neural Networks(2017).https://www.scopus.com/inward/record.uri?eid=2‐s2.0‐85048447329&partnerID=40&md5=83dcc2c11bbce0f023b788b5f78f3e54