Conference Proceedings
Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint
J Guo, J Li, H Fu, M Gong, K Zhang, D Tao
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | IEEE COMPUTER SOC | Published : 2022
Abstract
Unsupervised image-to-image (I21) translation aims to learn a domain mapping function that can preserve the semantics of the input images without paired data. However, because the underlying semantics distributions in the source and target domains are often mismatched, current distribution matching-based methods may distort the semantics when matching distributions, resulting in the inconsistency between the input and translated images, which is known as the semantics distortion problem. In this paper, we focus on the low-level I21 translation, where the structure of images is highly related to their semantics. To alleviate semantic distortions in such translation tasks without paired superv..
View full abstractGrants
Awarded by National Institutes of Health
Funding Acknowledgements
Mr Jiaxian Guo is supported in part by Australian Research Council Projects FL-170100117 and IH-180100002. Dr Mingming Gong is supported by Australian Research Council Project DE210101624. Prof Kun Zhang would like to acknowledge the support by the National Institutes of Health under Contract R01HL159805, by the NSF Convergence Accelerator Track-D award #2134901, and by the United States Air Force under Contract No. FA8650-17C7715.