论文浏览

【论文题目】Joint Multi-Feature Fusion and Attribute Relationships for Facial Attribute Prediction

【作    者】Pingyu Wang, Fei Su, Zhicheng Zhao        点击下载PDF全文

【关 键 字】Feature Fusion, Multi-Task, Attribute Prediction, Attribute Relationships, Online Batch Relation Loss

【发表刊物/会议】
    Visual Communications and Image Processing (VCIP 2017)

【摘    要】
     Predicting facial attributes from wild images is very challenging due to complex face variations. The key to this problem is to construct rich facial representations and take advantage of attribute relationships. In this paper, we propose a novel multi-task convolutional neural network (MTCNN) and a supervision signal called Online Batch Relation Loss (OBRL) for face attribute prediction in the wild. In particular, MTCNN builds informative facial features by embedding identity, age and race features from IdentityNet, AgeNet and RaceNet respectively. In addition, OBRL can diminish distribution shift of attribute relationships by mining attribute correlation within each mini-batch, while it penalizes the probability divergence between a pair of attributes. In order to learn discriminative attribute features, we feed AttributeNet with fused facial features and partition attributes into nine groups to share intra-group features and reduce redundant computation. Finally, AttributeNet is optimized with the joint supervision of Cross Entropy Loss and OBRL. Experiments on CelebA and LFWA show that the proposed method outperforms the state-of-the-art methods with a significant margin.

【发 表 年】2017

【发 表 月】12

【类    别】模式识别


Tel: 086-010-62283118 邮编:100876
地址:北京市海淀区西土城路10号北京邮电大学教二楼多媒体中心
北京市海淀区西土城路十号113#信箱
版权所有:北京邮电大学多媒体通信与模式识别研究室 京ICP证14002347号