中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Semi-supervised cross-modal image generation with generative adversarial networks

文献类型:期刊论文

作者Li D(李丹); Du CD(杜长德); He HG(何晖光)
刊名Pattern Recognition
出版日期2020
卷号100页码:107085
英文摘要

Cross-modal image generation is an important aspect of the multi-modal learning. Existing methods usually use the semantic feature to reduce the modality gap. Although these methods have achieved notable progress, there are still some limitations: (1) they usually use single modality information to learn the semantic feature; (2) they require the training data to be paired. To overcome these problems, we propose a novel semi-supervised cross-modal image generation method, which consists of two semantic networks and one image generation network. Specifically, in the semantic networks, we use image modality to assist non-image modality for semantic feature learning by using a deep mutual learning strategy. In the image generation network, we introduce an additional discriminator to reduce the image reconstruction loss. By leveraging large amounts of unpaired data, our method can be trained in a semi-supervised manner. Extensive experiments demonstrate the effectiveness of the proposed method.

URL标识查看原文
语种英语
源URL[http://ir.ia.ac.cn/handle/173211/51625]  
专题类脑智能研究中心_神经计算及脑机交互
通讯作者He HG(何晖光)
作者单位Institute of Automation,Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Li D,Du CD,He HG. Semi-supervised cross-modal image generation with generative adversarial networks[J]. Pattern Recognition,2020,100:107085.
APA Li D,Du CD,&He HG.(2020).Semi-supervised cross-modal image generation with generative adversarial networks.Pattern Recognition,100,107085.
MLA Li D,et al."Semi-supervised cross-modal image generation with generative adversarial networks".Pattern Recognition 100(2020):107085.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
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。