CyEDA : CYCLE OBJECT EDGE CONSISTENCY DOMAIN ADAPTATION
Paper in proceeding, 2022

Despite the advent of domain adaptation methods, most of them still struggle in preserving the instance level details of images when performing global level translation. While there are instance level translation methods that can retain the instance level details well, most of them require either pre-train
object detection/segmentation network and annotation labels. In this work, we propose a novel method namely CyEDA to perform global level domain adaptation that taking care of image contents without any pre-train networks integration or annotation labels. That is, we introduce masking and cycle-object edge consistency loss which exploit the preservation of image objects. We show that our approach is able to outperform other SOTAs in terms of image quality and FID score in both BDD100K and GTA datasets.

domain adaptation

image-to-image translation

Author

Jing Chong Beh

University of Malaya

Kam Woh Ng

University of Surrey

Jie Long Kew

University of Malaya

Che-Tsung Lin

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Shang-Hong Lai

Microsoft AI R&D Center

National Tsing Hua University

Christopher Zach

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Proceedings - International Conference on Image Processing, ICIP

15224880 (ISSN)

2986-2990
9781665496209 (ISBN)

International Conference on Image Processing
Bordeaux, France,

Subject Categories

Signal Processing

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/ICIP46576.2022.9897493

More information

Latest update

10/27/2023