UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models release_2bqjdjibonhdvl5x2vdxej4xfi

by Arvindkumar Krishnakumar, Viraj Prabhu, Sruthi Sudhakar, Judy Hoffman

Released as a article .

2021  

Abstract

Deep learning models have been shown to learn spurious correlations from data that sometimes lead to systematic failures for certain subpopulations. Prior work has typically diagnosed this by crowdsourcing annotations for various protected attributes and measuring performance, which is both expensive to acquire and difficult to scale. In this work, we propose UDIS, an unsupervised algorithm for surfacing and analyzing such failure modes. UDIS identifies subpopulations via hierarchical clustering of dataset embeddings and surfaces systematic failure modes by visualizing low performing clusters along with their gradient-weighted class-activation maps. We show the effectiveness of UDIS in identifying failure modes in models trained for image classification on the CelebA and MSCOCO datasets.
In text/plain format

Archived Files and Locations

application/pdf  39.4 MB
file_p72i3sthu5apfhuimvlgeriv6a
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-10-29
Version   v1
Language   en ?
arXiv  2110.15499v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bb779b2a-fbeb-49c0-9adb-a8c38ecb76ee
API URL: JSON