Crdoco: Pixel-level domain transfer with cross-domain consistency

Yun Chun Chen, Yen-Yu Lin, Ming Hsuan Yang, Jia Bin Huang

研究成果: Conference contribution同行評審

266 引文 斯高帕斯(Scopus)

摘要

Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e.g., synthetic to real images). The adapted representations often do not capture pixel-level domain shifts that are crucial for dense prediction tasks (e.g., semantic segmentation). In this paper, we present a novel pixel-wise adversarial domain adaptation algorithm. By leveraging image-to-image translation methods for data augmentation, our key insight is that while the translated images between domains may differ in styles, their predictions for the task should be consistent. We exploit this property and introduce a cross-domain consistency loss that enforces our adapted model to produce consistent predictions. Through extensive experimental results, we show that our method compares favorably against the state-of-the-art on a wide variety of unsupervised domain adaptation tasks.

原文English
主出版物標題Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
發行者IEEE Computer Society
頁面1791-1800
頁數10
DOIs
出版狀態Published - 6月 2019
事件32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, 美國
持續時間: 16 6月 201920 6月 2019

出版系列

名字Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
2019-June
ISSN(列印)1063-6919

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
國家/地區美國
城市Long Beach
期間16/06/1920/06/19

指紋

深入研究「Crdoco: Pixel-level domain transfer with cross-domain consistency」主題。共同形成了獨特的指紋。

引用此