Sketch-based Image Retrieval using Generative Adversarial Networks
文献类型:会议论文
作者 | Longteng,Guo1,3; Jing, Liu1; Yuhang, Wang1,3; Zhonghua, Luo2; Wei, Wen2; Hanqing, Lu1 |
出版日期 | 2017 |
会议日期 | 2017.10.23 |
会议地点 | 美国山景城 |
英文摘要 | For sketch-based image retrieval (SBIR), we propose a generative adversarial network trained on a large number of sketches and their corresponding real images. To imitate human search process, we attempt to match candidate images with the imaginary image in user's mind instead of the sketch query, i.e., not only the shape information of sketches but their possible content information are considered in SBIR. Specifically, a conditional generative adversarial network (cGAN) is employed to enrich the content information of sketches and recover the imaginary images, and two VGG-based encoders, which work on real and imaginary images respectively, are used to constrain their perceptual consistency from the view of feature representations. During SBIR, we first generate an imaginary image from a given sketch via cGAN, and then take the output of the learned encoder for imaginary images as the feature of the query sketch. Finally, we build an interactive SBIR system that shows encouraging performance. |
源URL | [http://ir.ia.ac.cn/handle/173211/44989] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
通讯作者 | Jing, Liu |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.Samsung R&D Institute 3.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Longteng,Guo,Jing, Liu,Yuhang, Wang,et al. Sketch-based Image Retrieval using Generative Adversarial Networks[C]. 见:. 美国山景城. 2017.10.23. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。