Revisiting Batch Normalization for Improving Corruption Robustness release_63q7gaqz55blfn6nw2lqnvljmm

by Philipp Benz, Chaoning Zhang, Adil Karjauv, In So Kweon

Released as a article .

2021  

Abstract

The performance of DNNs trained on clean images has been shown to decrease when the test images have common corruptions. In this work, we interpret corruption robustness as a domain shift and propose to rectify batch normalization (BN) statistics for improving model robustness. This is motivated by perceiving the shift from the clean domain to the corruption domain as a style shift that is represented by the BN statistics. We find that simply estimating and adapting the BN statistics on a few (32 for instance) representation samples, without retraining the model, improves the corruption robustness by a large margin on several benchmark datasets with a wide range of model architectures. For example, on ImageNet-C, statistics adaptation improves the top1 accuracy of ResNet50 from 39.2% to 48.7%. Moreover, we find that this technique can further improve state-of-the-art robust models from 58.1% to 63.3%.
In text/plain format

Archived Content

There are no accessible files associated with this release. You could check other releases for this work for an accessible version.

"Dark" Preservation Only
Save Paper Now!

Know of a fulltext copy of on the public web? Submit a URL and we will archive it

Type  article
Stage   submitted
Date   2021-01-28
Version   v4
Language   en ?
arXiv  2010.03630v4
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d42b8e0c-7cc0-47c5-8115-de4f84f04782
API URL: JSON