Compact class-conditional domain invariant learning for multi-class domain adaptation. (April 2021)

• Record Type: Journal Article
• Authors: Lee, Woojin; Kim, Hoki; Lee, Jaewook
• Is Part Of: Pattern recognition. Volume 112(2021)
• Publication Date: 2021-04
• Subjects: Domain adaptation -- Generalization bound -- Class-conditional domain invariant learning -- PAC learning complexity -- Transfer Learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107763
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Present new generalization risk bounds for multi-class domain adaptation. Proposed a novel learning method based on the risk bounds. Performed an empirical study on benchmarking data sets. Considering class-conditional domain invariance delivers better performances. Abstract: Neural network-based models have recently shown excellent performance in various kinds of tasks. However, a large amount of labeled data is required to train deep networks, and the cost of gathering labeled training data for every kind of domain is prohibitively expensive. Domain adaptation tries to solve this problem by transferring knowledge from labeled source domain data to unlabeled target domain data. Previous research tried to learn domain-invariant features of source and target domains to address this problem, and this approach has been used as a key concept in various methods. However, domain-invariant features do not mean that a classifier trained on source data can be directly applied to target data because it does not guarantee that data distribution of the same classes will be aligned across two domains. In this paper, we present novel generalization upper bounds for domain adaptation that motivates the need for class-conditional domain invariant learning. Based on this theoretical framework, we then propose a class-conditional domain invariant learning method that can learn a feature space in which features in the same class are expected to be mapped nearby. We empirically experimented that our model showed state-of-the-art performance on standard datasets and showed effectiveness by visualization of latent space.