Edge-Guided Cross-Domain Learning with Shape Regression for Sketch-Based Image Retrieval

Sketch-based image retrieval (SBIR) is a challenging task due to the cross-domain gap between sketch queries and natural images. In this paper, we propose a novel edge-guided cross-domain learning network to reduce the domain gap. In particular, edge maps extracted from natural images are introduced...

全面介紹

書目詳細資料

發表在:	IEEE Access
Main Authors:	Yuxin Song, Jianjun Lei, Bo Peng, Kaifu Zheng, Bolan Yang, Yalong Jia
格式:	Article
語言:	英语
出版:	IEEE 2019-01-01
主題:	Sketch-based image retrieval cross-domain learning CNN
在線閱讀:	https://ieeexplore.ieee.org/document/8664177/