4 papers
One-for-All: Towards Universal Domain Translation with a Single StyleGAN
Yong Du, Jiahui Zhan, Xinzhe Li +4
In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and…
UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching
Qingxuan Lv, Junyu Dong, Yuezun Li +4
Despite recent advances in stereo matching, the extension to intricate underwater settings remains unexplored, primarily owing to: 1) the reduced visibility, low contrast, and othe…
DomainForensics: Exposing Face Forgery across Domains via Bi-directional Adaptation
Qingxuan Lv, Yuezun Li, Junyu Dong +4
Recent DeepFake detection methods have shown excellent performance on public datasets but are significantly degraded on new forgeries. Solving this problem is important, as new for…
High-order Neighborhoods Know More: HyperGraph Learning Meets Source-free Unsupervised Domain Adaptation
Jinkun Jiang, Qingxuan Lv, Yuezun Li +4
Source-free Unsupervised Domain Adaptation (SFDA) aims to classify target samples by only accessing a pre-trained source model and unlabelled target samples. Since no source data i…