Learning to Weight Filter Groups for Robust Classification

Siyang Yuan, Yitong Li, Dong Wang, Ke Bai, Lawrence Carin, David Carlson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


In many real-world tasks, a canonical 'big data' problem is created by combining data from several individual groups or domains. Because test data will likely come from a new group of data, we want to utilize the grouped structure of our training data to enforce generalization between groups of data, not just individual samples. This can be viewed as a multiple-domain generalization problem. Specifically, the goal is to encourage generalization between previously seen labeled source data from multiple domains and unlabeled target domain data. To address this challenge, we introduce Domain-Specific Filter Group (DSFG), where each training domain has a unique filter group and each test data point is predicted by a weighted sum over the outputs of different domain filters. A separate neural network learns to estimate the appropriate filter group weights through a meta-learning strategy. Empirically, experiments on three benchmark datasets demonstrate improved performance compared to current state-of-the-art approaches.
Original languageEnglish (US)
Title of host publication2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Number of pages10
ISBN (Print)9781665409155
StatePublished - Jan 2022

Bibliographical note

KAUST Repository Item: Exported on 2022-03-21
Acknowledgements: The research was supported in part by DARPA, DOE, NIH, NSF and ONR. DC was supported by the National Institutes of Health under Award Number R01EB026937.


Dive into the research topics of 'Learning to Weight Filter Groups for Robust Classification'. Together they form a unique fingerprint.

Cite this