A Survey to Deep Facial Attribute Analysis

Facial attribute analysis has received considerable attention when deep learning techniques make remarkable breakthroughs in this field over the past few years. Deep learning based facial attribute analysis is comprised of two basic sub-issues: Facial Attribute Estimation (FAE), which recognizes whether facial attributes are present in given images, and Facial Attribute Manipulation (FAM), which synthesizes or removes desired facial attributes. In this paper, we provide a comprehensive survey on deep facial attribute analysis from the perspectives of both estimation and manipulation. First, we summarize that deep facial attribute analysis follows a general pipeline, which comprises two stages, i.e., data pre-processing and model construction. Meanwhile, the underlying theories of the two-stage pipeline are provided for both FAE and FAM, respectively. Second, we introduce commonly used datasets and performance metrics in facial attribute analysis. Third, we create a taxonomy of the state-of-the-arts and review FAE and FAM algorithms in detail. Furthermore, several additional facial attribute related issues are introduced, as well as relevant real-world applications. Finally, we discuss possible challenges and promising future research directions