Current Anomaly Detectors are Anomalous: On Semantic Treatment of OOD InputsDownload PDF

Published: 01 Feb 2023, Last Modified: 13 Feb 2023Submitted to ICLR 2023Readers: Everyone
Keywords: machine learning, training distribution, out-of-distribution, OODs, detection, semantic information
TL;DR: We propose that in-distribution should not be tied to the training distribution but to the distribution of semantic information in training data, and therefore OOD detection should be performed on the semantic information extracted from training data
Abstract: Machine learning models have achieved impressive performance across different modalities. It is well known that these models are prone to making mistakes on out-of-distribution inputs. OOD detection has, therefore, gained a lot of attention recently. We observe that most existing detectors use the distribution estimated by the training dataset for OOD detection. This can be a serious impediment since faulty OOD detectors can potentially restrict utility of the model. Such detectors, tied to the bias in data collection process, can be impermeable to inputs lying outside the training distribution but with the same semantic information (e.g., class labels) as the training data. We argue that in-distribution should not be tied to just the training distribution but to the distribution of the semantic information contained in the training data. To support our argument, we perform OOD detection on semantic information extracted from the training data of MNIST and COCO datasets, and show that it not only reduces false alarms but also significantly improves detection of OOD inputs with spurious features from training data.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning
15 Replies

Loading