Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation

Page view(s)
17
Checked on Feb 12, 2025
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
Title:
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
Journal Title:
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Keywords:
Publication Date:
15 January 2024
Citation:
Herath, S., Fernando, B., Abbasnejad, E., Hayat, M., Khadivi, S., Harandi, M., Rezatofighi, H., & Haffari, G. (2023, October 1). Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.01070
Abstract:
We propose an Unsupervised Domain Adaptation (UDA) method by making use of Energy-Based Learning (EBL) and demonstrate 1. EBL can be used to improve the instance selection for a self-training task on the unlabelled target domain, and 2. alignment and normalizing energy scores can learn domain-invariant representations. For the former, we show that an energy-based selection criterion can be used to model instance selections by mimicking the joint distribution between data and predictions in the target domain. As per learning domain invariant representations, we show that stable domain alignment can be achieved by a combined energy alignment and an energy normalization process. We implement our method in consistent with the vision-transformer (ViT) backbone and show that our proposed method can outperform state-of-the-art ViT based UDA methods on diverse benchmarks (DomainNet, Office-Home, and VISDA2017).
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - NRF Fellowship
Grant Reference no. : NRF-NRFF14-2022-0001
Description:
© 2024 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.
ISSN:
2380-7504
Files uploaded:

File Size Format Action
iccv-2023-energy-based-domain-adaptation.pdf 563.73 KB PDF Request a copy