SELF-BALANCED LEARNING FOR DOMAIN GENERALIZATION

Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Domain generalization aims to learn a prediction model on multi-domain source data such that the model can generalize to a target domain with unknown statistics. Most existing approaches have been developed under the assumption that the source data is well-balanced in terms of both domain and class. However, real-world training data collected with different composition biases often exhibits severe distribution gaps for domain and class, leading to substantial performance degradation. In this paper, we propose a self-balanced domain generalization framework that adaptively learns the weights of losses to alleviate the bias caused by different distributions of the multi-domain source data. The self-balanced scheme is based on an auxiliary reweighting network that iteratively updates the weight of loss conditioned on the domain and class information by leveraging balanced meta data. Experimental results demonstrate the effectiveness of our method overwhelming state-of-the-art works for domain generalization.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PublisherIEEE Computer Society
Pages779-783
Number of pages5
ISBN (Electronic)9781665441155
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
Duration: 19 Sep 202122 Sep 2021

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2021-September
ISSN (Print)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing, ICIP 2021
Country/TerritoryUnited States
CityAnchorage
Period19/09/2122/09/21

Keywords

  • Class imbalance
  • Domain generalization
  • Domain imbalance
  • Meta-learning

Fingerprint

Dive into the research topics of 'SELF-BALANCED LEARNING FOR DOMAIN GENERALIZATION'. Together they form a unique fingerprint.

Cite this