TrustMAE: A noise-resilient defect classification framework using memory-augmented auto-encoders with trust regions

Daniel Stanley Tan, Y.-C. Chen, T.P.-C. Chen, W.-C. Chen

Research output: Chapter in Book/Report/Conference proceedingConference Article in proceedingAcademicpeer-review

Abstract

In this paper, we propose a framework called Trust-MAE to address the problem of product defect classification. Instead of relying on defective images that are difficult to collect and laborious to label, our framework can accept datasets with unlabeled images. Moreover, unlike most anomaly detection methods, our approach is robust against noises, or defective images, in the training dataset. Our framework uses a memory-augmented auto-encoder with a sparse memory addressing scheme to avoid over-generalizing the auto-encoder, and a novel trust-region memory updating scheme to keep the noises away from the memory slots. The result is a framework that can reconstruct defect-free images and identify the defective regions using a perceptual distance network. When compared against various state-of-the-art baselines, our approach performs competitively under noise-free MVTec datasets. More importantly, it remains effective at a noise level up to 40% while significantly outperforming other baselines.
Original languageEnglish
Title of host publicationProceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision
Subtitle of host publicationWACV 2021
PublisherIEEE
Pages276-285
Number of pages10
ISBN (Electronic)978-1-6654-0477-8
ISBN (Print)978-1-6654-4640-2
DOIs
Publication statusPublished - 14 Jun 2021
Externally publishedYes
EventIEEE Winter Conference on Applications of Computer Vision - Waikoloa, United States
Duration: 3 Jan 20218 Jan 2021
https://ieeexplore.ieee.org/xpl/conhome/9423008/proceeding

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV 2021
Country/TerritoryUnited States
CityWaikoloa
Period3/01/218/01/21
Internet address

Fingerprint

Dive into the research topics of 'TrustMAE: A noise-resilient defect classification framework using memory-augmented auto-encoders with trust regions'. Together they form a unique fingerprint.

Cite this