CyEDA: Cycle-Object Edge Consistency Domain Adaptation
Lists
Only you see this
Abstract
A difficulty of global-level translation is to preserve instance-level details in an image. Although some instance level translation methods can retain the details, most of them require either pre-trained object detection/segmentation network or annotation labels. In this work, we propose a novel method namely CyEDA to perform global level domain adaptation that can preserve image contents without any pre-trained networks integration or annotation labels. Specifically, we introduce blending masks and cycle-object edge consistency loss which exploit the preservation of image objects. We show that our approach can outperform other SOTAs in terms of image quality and FID score in both BDD100K and GTA datasets. The code and pre-trained models are publicly available at https://github.com/bjc1999/CyEDA.
BibTeX
@inproceedings{beh2022cyeda,
author = {Jing Chong Beh and Kam Woh Ng and Jie-Long Kew and Che-Tsung Lin and Chee Seng Chan and Shang-Hong Lai and Christopher Zach},
title = {{CyEDA: Cycle-Object Edge Consistency Domain Adaptation}},
booktitle = {ICIP},
year = {2022},
doi = {10.1109/icip46576.2022.9897493},
}Loading related content...