Zero-Shot Out-of-Distribution Detection with Feature Correlations

View Researcher's Other Codes

Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).

Please contact us in case of a broken link from here

Authors Anonymous
Journal/Conference Name ICLR 2020 1
Paper Category
Paper Abstract When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions. Detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to detect OOD examples by identifying inconsistencies between activity patterns and class predicted. We find that characterizing activity patterns by feature correlations and identifying anomalies in pairwise feature correlation values can yield high OOD detection rates. We identify anomalies in the pairwise feature correlations by simply comparing each pairwise correlation value with its respective range observed over the training data. Unlike many approaches, this can be used with any pre-trained softmax classifier and does not require access to OOD data for fine-tuning hyperparameters, nor does it require OOD access for inferring parameters. The method is applicable across a variety of architectures and vision datasets and generally performs better than or equal to state-of-the-art OOD detection methods, including those that do assume access to OOD examples.
Date of publication 2020
Code Programming Language Jupyter Notebook
Comment

Copyright Researcher 2022