Skip to Main content Skip to Navigation
Conference papers

Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation

Abstract : Image-to-image translation architectures may have limited effectiveness in some circumstances. For example, while generating rainy scenarios, they may fail to model typical traits of rain as water drops, and this ultimately impacts the synthetic images realism. With our method, called domain bridge, web-crawled data are exploited to reduce the domain gap, leading to the inclusion of previously ignored elements in the generated images. We make use of a network for clear to rain translation trained with the domain bridge to extend our work to Unsupervised Domain Adaptation (UDA). In that context, we introduce an online multimodal style-sampling strategy, where image translation multimodality is exploited at training time to improve performances. Finally, a novel approach for self-supervised learning is presented, and used to further align the domains. With our contributions, we simultaneously increase the realism of the generated images, while reaching on par performances with respect to the UDA state-of-the-art, with a simpler approach.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-02436218
Contributor : Fabio Pizzati Connect in order to contact the contributor
Submitted on : Sunday, January 12, 2020 - 6:51:44 PM
Last modification on : Wednesday, June 8, 2022 - 12:50:05 PM

Links full text

Identifiers

Collections

Citation

Fabio Pizzati, Raoul de Charette, Michela Zaccaria, Pietro Cerri. Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation. Winter Conference on Applications of Computer Vision (WACV ’20), Mar 2020, Snowmass, United States. ⟨10.1109/WACV45572.2020.9093540⟩. ⟨hal-02436218⟩

Share

Metrics

Record views

79