@inproceedings{DBLP:conf/miccai/TanKHBK21,
  author    = {Jeremy Tan and
               Turkay Kart and
               Benjamin Hou and
               James Batten and
               Bernhard Kainz},
  title     = {MetaDetector: Detecting Outliers by Learning to Learn from Self-supervision},
  booktitle = {MIDOG/MOOD/Learn2Reg@MICCAI},
  series    = {Lecture Notes in Computer Science},
  volume    = {13166},
  pages     = {119--126},
  publisher = {Springer},
  year      = {2021},
  doi = {10.1007/978-3-030-97281-3\_18},
  url = {https://doi.org/10.1007/978-3-030-97281-3\_18},
  abstract = {Using self-supervision in anomaly detection can increase sensitivity to subtle irregularities, but sensitivity to some classes of outlier can reduce sensitivity to others. This work explores whether meta-learning can make self-supervised methods more adaptive. It constructs a few-shot task from the test input and normal reference images, then uses second-order gradients to learn how to adapt while applying strong regularization near the bottleneck of an encoder-decoder architecture.},
}