期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 40, 期 11, 页码 2597-2609出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2017.2738004
关键词
Face recognition; heterogeneous attribute estimation; attribute correlation; attribute heterogeneity; multi-task learning
资金
- National Basic Research Program of China (973 Program) [2015CB351802]
- Natural Science Foundation of China [61390511, 61732004, 61672496, 61650202]
- CAS-INRIA JRPs [GJHZ1843]
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 versus nominal and holistic versus local) 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 face attributes (MORPH II, LFW+, CelebA, LFWA, and FotW) show that the proposed approach has superior performance compared to state of the art. Finally, evaluations on a public-domain face database (LAP) with a single attribute show that the proposed approach has excellent generalization ability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据