Sparse Feature Representation Learning for Deep Face Gender Transfer
Sparse Feature Representation Learning for Deep Face Gender Transfer
复制标题
DOI：
10.1109/iccvw54120.2021.00454
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Xudong Liu;Ruizhe Wang;Hao Peng;Minglei Yin;Chih-Fan Chen;Xin Li
中科院分区：
文献类型：
--
作者：
Xudong Liu;Ruizhe Wang;Hao Peng;Minglei Yin;Chih-Fan Chen;Xin Li
为什么人们认为汤姆·汉克斯和朱丽叶特·刘易斯长得很像？我们能否在不改变身份信息的情况下修改人脸图像的性别外观？在给定的面部图像中是否有任何特定的特征导致女性气质/男性气质的感知？从计算机视觉和视觉感知的角度来看，这些问题都很有吸引力。为了阐明这些问题，我们建议开发一种基于 GAN 的面部性别迁移方法，并研究学习到的特征表示与面部性别感知的相关性。我们的主要贡献包括：1）在特征空间中具有专门定制的损失函数的架构设计，用于面部性别转移； 2）引入新颖的概率性别面具，以促进实现性别转移和身份保存的目标； 3）识别唯一负责面部性别感知的稀疏特征（256 个中的 20 个）。大量的实验结果不仅证明了所提出的面部性别转移技术的优越性（在重建图像的视觉质量方面），而且证明了性别特征表示学习的有效性（在学习的稀疏特征和感知的性别信息之间的高度相关性方面）。我们的研究结果似乎证实了心理学文献中关于面部可识别性和性别可分类性之间独立性的假设。我们预计这项工作将激发对不同面部感知属性（包括种族、年龄、吸引力和可信度）的更多计算研究。
Why do people think Tom Hanks and Juliette Lewis look alike? Can we modify the gender appearance of a face image without changing its identity information? Is there any specific feature responsible for the perception of femininity/masculinity in a given face image? Those questions are appealing from both computer vision and visual perception perspectives. To shed light upon them, we propose to develop a GAN based approach toward face gender transfer and study the relevance of learned feature representations to face gender perception. Our key contributions include: 1) an architecture design with specially tailored loss functions in the feature space for face gender transfer; 2) the introduction of a novel probabilistic gender mask to facilitate achieving both the objectives of gender transfer and identity preservation; and 3) identification of sparse features (≈ 20 out of 256) uniquely responsible for face gender perception. Extensive experimental results are reported to demonstrate not only the superiority of the proposed face gender transfer technique (in terms of visual quality of reconstructed images) but also the effectiveness of gender feature representation learning (in terms of the high correlation between the learned sparse features and the perceived gender information). Our findings seem to corroborate a hypothesis about the independence between face recognizability and gender classifiability in the literature of psychology. We expect this work will stimulate more computational studies of different face perception attributes including race, age, attractiveness, and trustworthiness.