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

10/23/2019
by   Fabio Pizzati, et al.
18

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 w.r.t. the UDA state-of-the-art, with a simpler approach.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 7

research
11/05/2021

Semantic Consistency in Image-to-Image Translation for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a s...
research
03/26/2021

Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching

Recently proposed DNN-based stereo matching methods that learn priors di...
research
12/16/2021

Improving Unsupervised Stain-To-Stain Translation using Self-Supervision and Meta-Learning

In digital pathology, many image analysis tasks are challenged by the ne...
research
09/04/2023

StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation

We introduce a novel training strategy for stereo matching and optical f...
research
03/17/2022

Synthetic-to-Real Domain Adaptation using Contrastive Unpaired Translation

The usefulness of deep learning models in robotics is largely dependent ...
research
09/20/2023

Self-supervised Domain-agnostic Domain Adaptation for Satellite Images

Domain shift caused by, e.g., different geographical regions or acquisit...
research
07/29/2021

Guided Disentanglement in Generative Networks

Image-to-image translation (i2i) networks suffer from entanglement effec...

Please sign up or login with your details

Forgot password? Click here to reset