ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization. (arXiv:2303.17354v3 [cs.CV] UPDATED)

In the realm of machine learning, the study of anomaly detection and
localization within image data has gained substantial traction, particularly
for practical applications such as industrial defect detection. While the
majority of existing methods predominantly use Convolutional Neural Networks
(CNN) as their primary network architecture, we introduce a novel approach
based on the Transformer backbone network. Our method employs a two-stage
incremental learning strategy. During the first stage, we train a Masked
Autoencoder (MAE) model solely on normal images. …

anomaly anomaly detection applications architecture arxiv autoencoder cnn convolutional neural networks data defect detection detection image images incremental industrial localization machine machine learning masked autoencoder network network architecture networks neural networks normal novel practical self-supervised learning stage strategy study supervised learning transformer