Face attribute estimation has many potential applications in video surveillance, face retrieval, and social media. While a number of methods have been proposed for face attribute estimation, most of them did not explicitly consider the attribute correlation and heterogeneity (e.g., ordinal vs. nominal attributes) during feature representation learning. In this paper, we present a Deep Multi-Task Learning (DMTL) approach to jointly estimate multiple heterogeneous attributes from a single face image. In DMTL, we tackle attribute correlation and heterogeneity with convolutional neural networks (CNNs) consisting of shared feature learning for all the attributes, and category-specific feature learning for heterogeneous attributes. We also introduce an unconstrained face database (LFW+), an extension of public-domain LFW, with heterogeneous demographic attributes (age, gender, and race) obtained via crowdsourcing. Experimental results on benchmarks with multiple heterogeneous attributes (LFW+ and MORPH II) show that the proposed approach has superior performance compared to state of the art. Finally, evaluations on public-domain face databases with multiple binary attributes (CelebA and LFWA) and a single attribute (LAP) show that the proposed approach has excellent generalization ability.

本文章提出了一种基于深度多任务学习的方法，使用卷积神经网络来估计单张人脸图像中的多个异质属性，并在MORPH II、LFW+等数据库上进行了实验，取得了优秀的性能。

深度多任务学习方法进行异质人脸属性估计