CAN-GAN: Conditioned-attention normalized GAN for face age synthesis

CAN-GAN: Conditioned-attention normalized GAN for face age synthesis
复制标题

CAN-GAN:用于面部年龄合成的条件注意归一化 GAN

DOI:
10.1016/j.patrec.2020.08.021
复制
发表时间:
2020-10
影响因子:
5.1
通讯作者:
Shu Xiangbo
Shu Xiangbo
中科院分区:
计算机科学3区
文献类型:
--
作者:
Shi Chenglong;Zhang Jiachao;Yao Yazhou;Sun Yunlian;Rao Huaming;Shu Xiangbo

文献摘要

参考文献

被引文献

相似文献

这项工作的目的是将输入的人脸自由地转换为老化的人脸,具有强大的身份保留、令人满意的老化效果和真实的视觉外观。见证了 GAN 在图像合成方面的成功,研究人员利用 GAN 来解决人脸老化合成问题。然而,大多数基于GAN的方法认为所有面部区域的衰老变化是相等的,忽略了不同面部区域具有不同的衰老速度和衰老模式的事实。为此,我们提出了一种新颖的条件注意力标准化 GAN(CAN-GAN),用于年龄合成,利用两个年龄组之间的衰老差异来捕获具有不同注意力因素的面部衰老区域。特别是,设计了一个新的条件注意力归一化(CAN)层来增强人脸的衰老相关信息,同时通过注意力图平滑人脸的衰老无关信息。由于不同的面部属性有助于区分不同程度的年龄组,因此我们进一步提出了一种贡献感知年龄分类器(CAAC),它可以精细地衡量面部向量元素在年龄分类方面的重要性。对几个常用数据集的定性和定量实验表明,与其他竞争方法相比,CAN-GAN 具有先进性。
This work aims to freely translate an input face to an aging face with robust identity preservation, satisfying aging effect and authentic visual appearance. Witnessing the success of GAN in image synthesis, researchers employ GAN to address the problem of face aging synthesis. However, most GAN-based methods hold that the aging changing of all facial regions is equal, which ignores the fact that different facial regions have distinct aging speeds and aging patterns. To this end, we propose a novel Conditioned-Attention Normalization GAN (CAN-GAN) for age synthesis by leveraging the aging difference between two age groups to capture facial aging regions with different attention factors. In particular, a new Conditioned-Attention Normalization (CAN) layer is designed to enhance the aging-relevant information of face, while smoothing the aging-irrelevant information of face by attention map. Since different facial attributes contribute to the discrimination of age groups with divers degrees, we further present a Contribution-Aware Age Classifier (CAAC) that finely measures the importance of face vector’s elements in terms of the age classification. Qualitative and quantitative experiments on several commonly-used datasets show the advance of CAN-GAN compared with the other competitive methods.
DOI: 10.1016/j.neucom.2016.01.101
发表时间: 2016-10
期刊: Neurocomputing
影响因子: 6
作者:
Xiangbo Shu;Guosen Xie;Zechao Li;Jinhui Tang
通讯作者: Jinhui Tang
DOI: 10.1109/icccnt56998.2023.10306417
发表时间: 2022-02
期刊: 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)
影响因子: --
作者:
Gilad Cohen;Raja Giryes
通讯作者: Gilad Cohen;Raja Giryes
DOI: 10.1016/j.patcog.2015.12.015
发表时间: 2016-11
期刊: Pattern Recognit.
影响因子: --
作者:
Xiangbo Shu;Jinhui Tang;Hanjiang Lai;Zhiheng Niu;Shuicheng Yan
通讯作者: Xiangbo Shu;Jinhui Tang;Hanjiang Lai;Zhiheng Niu;Shuicheng Yan
DOI: 10.1109/tpami.2012.22
发表时间: 2012-11
影响因子: 23.6
作者:
Jin-Li Suo;Xilin Chen;S. Shan;Wen Gao;Qionghai Dai
通讯作者: Jin-Li Suo;Xilin Chen;S. Shan;Wen Gao;Qionghai Dai
DOI: 10.1109/iccv.2015.452
发表时间: 2015-10
期刊: 2015 IEEE International Conference on Computer Vision (ICCV)
影响因子: --
作者:
Xiangbo Shu;Jinhui Tang;Hanjiang Lai;Luoqi Liu;Shuicheng Yan
通讯作者: Xiangbo Shu;Jinhui Tang;Hanjiang Lai;Luoqi Liu;Shuicheng Yan