Prototypical Partial Optimal Transport for Universal Domain Adaptation
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (9) , 10852-10860
Abstract
Universal domain adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without requiring the same label sets of both domains. The existence of domain and category shift makes the task challenging and requires us to distinguish “known” samples (i.e., samples whose labels exist in both domains) and “unknown” samples (i.e., samples whose labels exist in only one domain) in both domains before reducing the domain gap. In this paper, we consider the problem from the point of view of distribution matching which we only need to align two distributions partially. A novel approach, dubbed mini-batch Prototypical Partial Optimal Transport (m-PPOT), is proposed to conduct partial distribution alignment for UniDA. In training phase, besides minimizing m-PPOT, we also leverage the transport plan of m-PPOT to reweight source prototypes and target samples, and design reweighted entropy loss and reweighted cross-entropy loss to distinguish “known” and “unknown” samples. Experiments on four benchmarks show that our method outperforms the previous state-of-the-art UniDA methods.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- On the Effectiveness of Image Rotation for Open Set Domain Adaptation2020
- Prevalence of neural collapse during the terminal phase of deep learning trainingProceedings of the National Academy of Sciences of the United States of America, 2020
- Transferrable Prototypical Networks for Unsupervised Domain Adaptation2019
- Separate to Adapt: Open Set Domain Adaptation via Progressive Separation2019
- Partial Adversarial Domain Adaptation2018
- Open Set Domain Adaptation by Backpropagation2018
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation2018
- Importance Weighted Adversarial Nets for Partial Domain Adaptation2018
- Partial Transfer Learning with Selective Adversarial Networks2018
- A theory of learning from different domainsMachine Learning, 2009