Learning low-shot generative networks for cross-domain data

Hsuan Kai Kao, Cheng Che Lee, Wei Chen Chiu

研究成果: Conference contribution同行評審

摘要

We tackle a novel problem of learning generators for cross-domain data under a specific scenario of low-shot learning. Basically, given a source domain with sufficient amount of training data, we aim to transfer the knowledge of its generative process to another target domain, which not only has few data samples but also contains the domain shift with respect to the source domain. This problem has great potential in practical use and is different from the well-known image translation task, as the target-domain data can be generated without requiring any source-domain ones and the large data consumption for learning target-domain generator can be alleviated. Built upon a cross-domain dataset where (1) each of the low shots in the target domain has its correspondence in the source and (2) these two domains share the similar content information but different appearance, two approaches are proposed: a Latent-Disentanglement-Orientated model (LaDo) and a Generative-Hierarchy-Oriented (GenHo) model. Our LaDo and GenHo approaches address the problem from different perspectives, where the former relies on learning the disentangled representation composed of domain-invariant content features and domain-specific appearance ones; while the later decomposes the generative process of a generator into two parts for synthesizing the content and appearance sequentially. We perform extensive experiments under various settings of cross-domain data and show the efficacy of our models for generating target-domain data with the abundant content variance as in the source domain, which lead to the favourable performance in comparison to several baselines.

原文English
主出版物標題Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
發行者Institute of Electrical and Electronics Engineers Inc.
頁面6818-6825
頁數8
ISBN(電子)9781728188089
DOIs
出版狀態Published - 2020
事件25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italy
持續時間: 10 1月 202115 1月 2021

出版系列

名字Proceedings - International Conference on Pattern Recognition
ISSN(列印)1051-4651

Conference

Conference25th International Conference on Pattern Recognition, ICPR 2020
國家/地區Italy
城市Virtual, Milan
期間10/01/2115/01/21

指紋

深入研究「Learning low-shot generative networks for cross-domain data」主題。共同形成了獨特的指紋。

引用此