Timezone: »

Domain Generalization by Learning and Removing Domain-specific Features
Yu Ding · Lei Wang · Bin Liang · Shuming Liang · Yang Wang · Fang Chen


Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen domains. In this paper, we propose a new approach that aims to explicitly remove domain-specific features for domain generalization. Following this approach, we propose a novel framework called Learning and Removing Domain-specific features for Generalization (LRDG) that learns a domain-invariant model by tactically removing domain-specific features from the input images. Specifically, we design a classifier to effectively learn the domain-specific features for each source domain, respectively. We then develop an encoder-decoder network to map each input image into a new image space where the learned domain-specific features are removed. With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification. Extensive experiments demonstrate that our framework achieves superior performance compared with state-of-the-art methods.

Author Information

Yu Ding (University of Wollongong)
Lei Wang (University of Wollonong)
Bin Liang (University of Technology Sydney)
Shuming Liang (University of Technology Sydney)
Yang Wang (University of Technology Sydney)
Fang Chen (University of Technology Sydney (UTS))

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors