Transfer representation-learning for anomaly detection
Jerone T. A. Andrews, Thomas Tanay, E. Morton, LD Griffin · UCL Discovery (University College London) · 2016
We evaluate transfer representation-learning for anomaly detection using convolutional neural networks by: (i) transfer learning from pretrained networks, and (ii) transfer learning from an auxiliary task by defining sub-categories of the normal class. We empirically show that both approaches offer viable representations for the task of anomaly detection, without explicitly imposing a prior on the data.