-
[pdf]
[supp]
[code]
[bibtex]@InProceedings{Long_2022_ACCV, author = {Long, Jun and Yang, Yuxi and Hua, Liujie and Ou, Yiqi}, title = {Self-Supervised Augmented Patches Segmentation for Anomaly Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {1926-1941} }
Self-Supervised Augmented Patches Segmentation for Anomaly Detection
Abstract
In this paper, our goal is to detect unknown defects in high-
resolution images in the absence of anomalous data. Anomaly detec-
tion is usually performed at image-level or pixel-level. Considering that
pixel-level anomaly classification achieves better representation learning
in a finer-grained manner, we regard data augmentation transforms as
a self-supervised segmentation task from which to extract the critical
and representative information from images. Due to the unpredictabil-
ity of anomalies in real scenarios, we propose a novel abnormal sam-
ple simulation strategy which augmented patches are randomly pasted
to original image to create a generalized anomalous pattern. Following
the framework of self-supervised, segmenting augmented patches is used
as a proxy task in the training phase to extract representation sep-
arating normal and abnormal patterns, thus constructing a one-class
classifier with a robust decision boundary. During the inference phase,
the classifier is used to perform anomaly detection on the test data,
while directly determining regions of unknown defects in an end-to-end
manner. Our experimental results on MVTec AD dataset and BTAD
dataset demonstrate the proposed SSAPS outperforms any other self-
supervised based methods in anomaly detection. Code is available at
https://github.com/BadSeedX/SSAPS.
Related Material