University of Oulu

Wanxia Deng, Yawen Cui, Zhen Liu, Gangyao Kuang, Dewen Hu, Matti Pietikäinen, and Li Liu. 2021. Informative Class-Conditioned Feature Alignment for Unsupervised Domain Adaptation. Proceedings of the 29th ACM International Conference on Multimedia. Association for Computing Machinery, New York, NY, USA, 1303–1312. DOI:

Informative class-conditioned feature alignment for unsupervised domain adaptation

Saved in:
Author: Deng, Wanxia1; Cui, Yawen2; Liu, Zhen1;
Organizations: 1National University of Defense Technology, Changsha, Hunan, China
2University of Oulu, Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 5.7 MB)
Persistent link:
Language: English
Published: Association for Computing Machinery, 2021
Publish Date: 2022-03-01


The goal of unsupervised domain adaptation is to learn a task classifier that performs well for the unlabeled target domain by borrowing rich knowledge from a well-labeled source domain. Although remarkable breakthroughs have been achieved in learning transferable representation across domains, two bottlenecks remain to be further explored. First, many existing approaches focus primarily on the adaptation of the entire image, ignoring the limitation that not all features are transferable and informative for the object classification task. Second, the features of the two domains are typically aligned without considering the class labels; this can lead the resulting representations to be domain-invariant but non-discriminative to the category. To overcome the two issues, we present a novel Informative Class-Conditioned Feature Alignment (IC2FA) approach for UDA, which utilizes a twofold method: informative feature disentanglement and class-conditioned feature alignment, designed to address the above two challenges, respectively. More specifically, to surmount the first drawback, we cooperatively disentangle the two domains to obtain informative transferable features; here, Variational Information Bottleneck (VIB) is employed to encourage the learning of task-related semantic representations and suppress task-unrelated information. With regard to the second bottleneck, we optimize a new metric, termed Conditional Sliced Wasserstein Distance (CSWD), which explicitly estimates the intra-class discrepancy and the inter-class margin. The intra-class and inter-class CSWDs are minimized and maximized, respectively, to yield the domain-invariant discriminative features. IC2FA equips class-conditioned feature alignment with informative feature disentanglement and causes the two procedures to work cooperatively, which facilitates informative discriminative features adaptation. Extensive experimental results on three domain adaptation datasets confirm the superiority of IC2FA.

see all

ISBN: 978-1-4503-8651-7
Pages: 1303 - 1312
DOI: 10.1145/3474085.3475579
Host publication: Proceedings of the 29th ACM International Conference on Multimedia. Association for Computing Machinery, MM 2021
Conference: ACM International Conference on Multimedia
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: This work was partially supported by the Academy of Finland under grant 331883, and the National Natural Science Foundation of China under Grant 61872379, 62022091 and 71701205.
Academy of Finland Grant Number: 331883
Detailed Information: 331883 (Academy of Finland Funding decision)
Copyright information: © 2021 Association for Computing Machinery. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 29th ACM International Conference on Multimedia,