Implementation and Validation of non-semantic Out-of-Distribution Detection on Image Data in Manufacturing

Simple item page
dc.contributor.authorJin, Meng
dc.contributor.authorRajesh, Mehta Dharmil
dc.contributor.authorXing, Wenting
dc.contributor.authorSchniertshauer, Johannes
dc.contributor.authorNeuhüttler, Jens
dc.contributor.authorZimmermann, Felix
dc.date.accessioned2022-12-27T19:23:10Z
dc.date.available2022-12-27T19:23:10Z
dc.date.issued2023-01-03
dc.description.abstractSmall changes in the production environment can have a negative impact on the performance of machine learning models. This study investigates the feasibility of various methods for detecting non-semantic Out-of-Distribution (OOD) cases in input images, which could be caused by hardware-side malfunctions, such as a defective camera flash. For this purpose, we design four experiments based on a real-world computer vision use case to simulate hardware problems that may occur in manufacturing and verify the performance of the various methods for detecting OOD cases. Furthermore, we explore the optimal sample size of input data to ensure that OOD cases can be found efficiently and successfully. The experimental results show that the tested methods can effectively and correctly detect the presence of non-semantic OOD data. The next step is to focus on securing ML models to identify malignant OOD cases, which negatively affects the performance of deep learning models.
dc.format.extent10
dc.identifier.doi10.24251/HICSS.2023.807
dc.identifier.isbn978-0-9981331-6-4
dc.identifier.other95b20f17-2607-44d1-b5e1-0212daea0635
dc.identifier.urihttps://hdl.handle.net/10125/103441
dc.language.isoeng
dc.relation.ispartofProceedings of the 56th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectCybersecurity and Software Assurance
dc.subjectai security
dc.subjectcomputer vision
dc.subjectmanufacturing
dc.subjectout-of-distribution detection
dc.titleImplementation and Validation of non-semantic Out-of-Distribution Detection on Image Data in Manufacturing
dc.type.dcmitext
prism.startingpage6675

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0650.pdf
Size:
996.83 KB
Format:
Adobe Portable Document Format
Download

Collections

Cybersecurity and Software Assurance