Self-Supervised Training with Autoencoders for Visual Anomaly Detection. (arXiv:2206.11723v2 [cs.CV] UPDATED)

Deep convolutional autoencoders provide an effective tool for learning
non-linear dimensionality reduction in an unsupervised way. Recently, they have
been used for the task of anomaly detection in the visual domain. By optimising
for the reconstruction error using anomaly-free examples, the common belief is
that a trained network will have difficulties to reconstruct anomalous parts
during the test phase. This is usually done by controlling the capacity of the
network by either reducing the size of the bottleneck layer or …

anomaly anomaly detection arxiv cv detection training