Contrastive attention network with dense field estimation for face completion | |
Ma, Xin1,2,3,4; Zhou, Xiaoqiang2,3,4,6; Huang, Huaibo1,2,3,4; Jia, Gengyun1,2,3,4; Chai, Zhenhua5; Wei, Xiaolin5 | |
发表期刊 | PATTERN RECOGNITION |
ISSN | 0031-3203 |
2022-04-01 | |
卷号 | 124页码:13 |
摘要 | Most modern face completion approaches adopt an autoencoder or its variants to restore missing regions in face images. Encoders are often utilized to learn powerful representations that play an important role in meeting the challenges of sophisticated learning tasks. Specifically, various kinds of masks are often presented in face images in the wild, forming complex patterns, especially in this hard period of COVID19. It's difficult for encoders to capture such powerful representations under this complex situation. To address this challenge, we propose a self-supervised Siamese inference network to improve the generalization and robustness of encoders. It can encode contextual semantics from full-resolution images and obtain more discriminative representations. To deal with geometric variations of face images, a dense correspondence field is integrated into the network. We further propose a multi-scale decoder with a novel dual attention fusion module (DAF), which can combine the restored and known regions in an adaptive manner. This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images. Extensive experiments clearly demonstrate that the proposed approach not only achieves more appealing results compared with state-of-the-art methods but also improves the performance of masked face recognition dramatically. (c) 2021 Elsevier Ltd. All rights reserved. |
关键词 | Face completion Unsupervised learning Attention mechanism 3D Face analysis |
DOI | 10.1016/j.patcog.2021.108465 |
关键词[WOS] | ADVERSARIAL NETWORK ; IMAGE |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundatio of China[62006228] |
项目资助者 | National Natural Science Foundatio of China |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000736980400001 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47140 |
专题 | 模式识别实验室 |
通讯作者 | Ma, Xin |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.NLPR, Beijing, Peoples R China 3.CEBSIT, Beijing, Peoples R China 4.CASIA, CRIPAC, Beijing, Peoples R China 5.Visual Intelligence Dept, Meituan, Peoples R China 6.Univ Sci & Technol China, Beijing, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ma, Xin,Zhou, Xiaoqiang,Huang, Huaibo,et al. Contrastive attention network with dense field estimation for face completion[J]. PATTERN RECOGNITION,2022,124:13. |
APA | Ma, Xin,Zhou, Xiaoqiang,Huang, Huaibo,Jia, Gengyun,Chai, Zhenhua,&Wei, Xiaolin.(2022).Contrastive attention network with dense field estimation for face completion.PATTERN RECOGNITION,124,13. |
MLA | Ma, Xin,et al."Contrastive attention network with dense field estimation for face completion".PATTERN RECOGNITION 124(2022):13. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
1-s2.0-S003132032100(3539KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论