Structure Preserving Generative Cross-Domain Learning

Haifeng Xia, Zhengming Ding; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 4364-4373

Unsupervised domain adaptation (UDA) casts a light when dealing with insufficient or no labeled data in the target domain by exploring the well-annotated source knowledge in different distributions. Most research efforts on UDA explore to seek a domain-invariant classifier over source supervision. However, due to the scarcity of label information in the target domain, such a classifier has a lack of ground-truth target supervision, which dramatically obstructs the robustness and discrimination of the classifier. To this end, we develop a novel Generative cross-domain learning via Structure-Preserving (GSP), which attempts to transform target data into the source domain in order to take advantage of source supervision. Specifically, a novel cross-domain graph alignment is developed to capture the intrinsic relationship across two domains during target-source translation. Simultaneously, two distinct classifiers are trained to trigger the domain-invariant feature learning both guided with source supervision, one is a traditional source classifier and the other is a source-supervised target classifier. Extensive experimental results on several cross-domain visual benchmarks have demonstrated the effectiveness of our model by comparing with other state-of-the-art UDA algorithms.