Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation
Changjae Kim (DGIST), Seunghun Lee (DGIST),* Sunghoon Im (DGIST)
The 34th British Machine Vision Conference
Abstract
In this paper, we present a novel multi-target domain adaptation (MTDA) method that adapts a single model to multiple domains with class-wise attribute transfer. To achieve this, we propose a high-precision pseudo labeling method for target domain images by utilizing cross-domain correspondence matching, which matches a target region to the most similar source region. Then, we propose class-wise image translation using the pseudo labels to avoid the problem of transferring characteristics between different classes and to allow translation between the same classes. Lastly, we introduce cross-domain feature consistency to learn the different characteristics of each target domain. Extensive experiments on the various complex driving scene show that ours achieves better performance than other state-of-the-art methods. The dense ablation study demonstrates the effectiveness of the proposed method.Video
Citation
@inproceedings{Kim_2023_BMVC,
author = {Changjae Kim and Seunghun Lee and Sunghoon Im},
title = {Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0633.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by