Trusted Data Anomaly Detection (TaDA) in Ground Truth Image Data

Date
2022-10
Language
American English
Embargo Lift Date
Committee Members
Degree
Degree Year
Department
Grantor
Journal Title
Journal ISSN
Volume Title
Found At
IEEE
Can't use the file because of accessibility barriers? Contact us with the title of the item, permanent link, and specifics of your accommodation need.
Abstract

Current state-of-the-art Artificial Intelligence (AI) anomaly detection from images is primarily used for defect detection and relies on relatively homogeneous datasets of images with similar foregrounds and backgrounds. This type of anomaly detection uses human labelled ground-truth data. In our research, we have extremely heterogeneous datasets and want to identify outliers. We use self-supervised Variational Autoencoders (VAEs) to identify anomalies in the latent vector feature space. Understanding the outliers in a large training data set is important for establishing trustworthiness of the AI models learned from these data, a strong requirement for military AI applications. Our study uses 8984 examples from Kaggle military planes and 4300 examples from Kaggle landscape data. We present the results of the combined heterogeneous dataset on the localized methods, with one such result exhibiting inliers as landscapes/backgrounds and outliers as all aircraft, detecting aircraft as anomalies with a 0.87 AUC. Results also include the inter-class AUC across the different aircraft classes. Our contribution to the state-of-the-art is to apply isolation forests to the latent space data after UMAP embeddings in a strongly heterogeneous image dataset for military applications to identify anomalies.

Description
item.page.description.tableofcontents
item.page.relation.haspart
Cite As
Boler, W., Dale, A., & Christopher, L. (2022). Trusted Data Anomaly Detection (TaDA) in Ground Truth Image Data. 2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 1–6. https://doi.org/10.1109/AIPR57179.2022.10092217
ISSN
Publisher
Series/Report
Sponsorship
Major
Extent
Identifier
Relation
Journal
2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)
Source
Author
Alternative Title
Type
Article
Number
Volume
Conference Dates
Conference Host
Conference Location
Conference Name
Conference Panel
Conference Secretariat Location
Version
Author's manuscript
Full Text Available at
This item is under embargo {{howLong}}