University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Episodic Training for Domain Generalization

Song, Yi-Zhe (2019) Episodic Training for Domain Generalization In: International Conference on Computer Vision (ICCV 2019), 27 Oct - 02 Nov 2019, Seoul, South Korea.

[img]
Preview
Text
Episodic Training for Domain Generalization.pdf - Accepted version Manuscript

Download (454kB) | Preview

Abstract

Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training domains. The simple approach of aggregating data from all source domains and training a single deep neural network end-to-end on all the data provides a surprisingly strong baseline that surpasses many prior published methods. In this paper we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime. Specifically, we decompose a deep network into feature extractor and classifier components, and then train each component by simulating it interacting with a partner who is badly tuned for the current domain. This makes both components more robust, ultimately leading to our networks producing state-of-the-art performance on three DG benchmarks. Furthermore, we consider the pervasive workflow of using an ImageNet trained CNN as a fixed feature extractor for downstream recognition tasks. Using the Visual Decathlon benchmark, we demonstrate that our episodic-DG training improves the performance of such a general purpose feature extractor by explicitly training a feature for robustness to novel problems. This shows that DG training can benefit standard practice in computer vision.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Song, Yi-Zhey.song@surrey.ac.uk
Date : 27 October 2019
Copyright Disclaimer : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Related URLs :
Depositing User : Clive Harris
Date Deposited : 20 Aug 2019 09:35
Last Modified : 28 Oct 2019 09:44
URI: http://epubs.surrey.ac.uk/id/eprint/852445

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800