Abstract
In multimedia analysis, one objective of unsupervised visual domain adaptation is to train a classifier that works well on a target domain given labeled source samples and unlabeled target samples. Feature alignment of two domains is the key issue which should be addressed to achieve this objective. Inspired by the recent study of Generative Adversarial Networks (GAN) in domain adaptation, this paper proposes a new model based on Generative Adversarial Network, named Hierarchical Adversarial Deep Network (HADN), which jointly optimizes the feature-level and pixel-level adversarial adaptation within a hierarchical network structure. Specifically, the hierarchical network structure ensures that the knowledge from pixel-level adversarial adaptation can be back propagated to facilitate the feature-level adaptation, which achieves a better feature alignment under the constraint of pixel-level adversarial adaptation. Extensive experiments on various visual recognition tasks show that the proposed method performs favorably against or better than competitive state-of-the-art methods.
Original language | English |
---|---|
Title of host publication | MM 2018 - Proceedings of the 2018 ACM Multimedia Conference |
Publisher | Association for Computing Machinery (ACM) |
Pages | 220-228 |
Number of pages | 9 |
ISBN (Electronic) | 9781450356657 |
DOIs | |
Publication status | Published - 15 Oct 2018 |
Event | 26th ACM Multimedia conference, MM 2018 - Seoul, Korea, Republic of Duration: 22 Oct 2018 → 26 Oct 2018 https://dl.acm.org/doi/proceedings/10.1145/3240508 (Link to conference proceedings) |
Publication series
Name | MM 2018 - Proceedings of the 2018 ACM Multimedia Conference |
---|
Conference
Conference | 26th ACM Multimedia conference, MM 2018 |
---|---|
Country/Territory | Korea, Republic of |
City | Seoul |
Period | 22/10/18 → 26/10/18 |
Internet address |
|
Scopus Subject Areas
- Computer Graphics and Computer-Aided Design
- Human-Computer Interaction
User-Defined Keywords
- Deep learning
- Generative Adversarial Network
- Unsupervised domain adaptation