Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation

Yufei Wang, Haoliang Li, Lap Pui Chau, Alex C. Kot

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

25 Citations (Scopus)

Abstract

Though convolutional neural networks are widely used in different tasks, lack of generalization capability in the absence of sufficient and representative data is one of the challenges that hinders their practical application. In this paper, we propose a simple, effective, and plug-and-play training strategy named Knowledge Distillation for Domain Generalization (KDDG) which is built upon a knowledge distillation framework with the gradient filter as a novel regularization term. We find that both the "richer dark knowledge"from the teacher network, as well as the gradient filter we proposed, can reduce the difficulty of learning the mapping which further improves the generalization ability of the model. We also conduct experiments extensively to show that our framework can significantly improve the generalization capability of deep neural networks in different tasks including image classification, segmentation, reinforcement learning by comparing our method with existing state-of-the-art domain generalization techniques. Last but not the least, we propose to adopt two metrics to analyze our proposed method in order to better understand how our proposed method benefits the generalization capability of deep neural networks.

Original languageEnglish
Title of host publicationMM 2021 - Proceedings of the 29th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages2595-2604
Number of pages10
ISBN (Electronic)9781450386517
DOIs
Publication statusPublished - 17 Oct 2021
Externally publishedYes
Event29th ACM International Conference on Multimedia, MM 2021 - Virtual, Online, China
Duration: 20 Oct 202124 Oct 2021

Publication series

NameMM 2021 - Proceedings of the 29th ACM International Conference on Multimedia

Conference

Conference29th ACM International Conference on Multimedia, MM 2021
Country/TerritoryChina
CityVirtual, Online
Period20/10/2124/10/21

Keywords

  • domain generalization
  • knowledge distillation
  • robustness

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation'. Together they form a unique fingerprint.

Cite this