About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Chandramouli Shama Sastry
- sl:arxiv_num : 1912.12510
- sl:arxiv_published : 2019-12-28T19:44:03Z
- sl:arxiv_summary : 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 Gram matrices and
identifying anomalies in gram matrix values can yield high OOD detection rates.
We identify anomalies in the gram matrices by simply comparing each 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, for the important and surprisingly hard
task of detecting far-from-distribution out-of-distribution examples, it
generally performs better than or equal to state-of-the-art OOD detection
methods (including those that do assume access to OOD examples).@en
- sl:arxiv_title : Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices@en
- sl:arxiv_updated : 2020-01-09T15:17:55Z
- sl:bookmarkOf : https://arxiv.org/abs/1912.12510
- sl:creationDate : 2020-01-15
- sl:creationTime : 2020-01-15T13:04:14Z
Documents with similar tags (experimental)