University of Leicester
Browse

Robust Ensembling Network for Unsupervised Domain Adaptation

Download (10.09 MB)
conference contribution
posted on 2021-09-01, 08:52 authored by H Sun, L Lin, N Liu, Huiyu Zhou

Recently, in order to address the unsupervised domain adaptation (UDA) problem, extensive studies have been proposed to achieve transferrable models. Among them, the most prevalent method is adversarial domain adaptation, which can shorten the distance between the source domain and the target domain. Although adversarial learning is very effective, it still leads to the instability of the network and the drawbacks of confusing category information. In this paper, we propose a Robust Ensembling Network (REN) for UDA, which applies a robust time ensembling teacher network to learn global information for domain transfer. Specifically, REN mainly includes a teacher network and a student network, which performs standard domain adaptation training and updates weights of the teacher network. In addition, we also propose a dual-network conditional adversarial loss to improve the ability of the discriminator. Finally, for the purpose of improving the basic ability of the student network, we utilize the consistency constraint to balance the error between the student network and the teacher network. Extensive experimental results on several UDA datasets have demonstrated the effectiveness of our model by comparing with other state-of-the-art UDA algorithms.

History

Author affiliation

School of Informatics, University of Leicester

Source

The 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI - 2021), November 8th-12th, 2021. (Virtual) Hanoi, Vietnam.

Version

  • AM (Accepted Manuscript)

Published in

Lecture Notes in Computer Science

Volume

13032

Pagination

530-543

Publisher

Springer

isbn

978-3-030-89363-7

Acceptance date

2021-08-09

Copyright date

2021

Available date

2022-09-21

Temporal coverage: start date

2021-11-08

Temporal coverage: end date

2021-11-12

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC