arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1804.02810cs.CV
收藏

一种用于人脸属性预测的多任务张量相关神经网络

A Novel Multi-Task Tensor Correlation Neural Network for Facial Attribute Prediction

Hunan University(湖南大学);National University of Defense Technology(国防科技大学);University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校)

Mingxing Duan, Kenli Li, Qi Tian

摘要:

人脸多属性预测从多任务学习(MTL)中受益匪浅,MTL同时学习多个人脸属性,以实现不同属性的共享或相互关联的表示。最广泛使用的MTL卷积神经网络是通过共享所有卷积层并在完全连接的层处针对特定任务的损失进行分裂来进行理论或经验设计的。然而,将不同属性的所有低级和中级特性视为相同是不恰当的,尤其是当这些属性只是松散相关时。本文提出了一种新的多属性张量相关神经网络(MTCN)用于人脸属性预测。该结构共享低级特征中的信息(例如,前两个卷积层)但将其拆分为高级特征(例如,从第三卷积层到全连接层)。同时,在高级特征提取期间,每个子网络(例如,性别网,性别网,.和Smile-Net)从其他网络中挖掘密切相关的特征以增强其特征。然后,我们使用一种新的张量相关分析算法(NTCCA)的微调子网络的C9层的功能到一个高度相关的空间。最后基于相关矩阵进行人脸属性预测。在具有多个人脸属性的基准测试(CelebA和LFWA)上的实验结果表明,该方法与最先进的方法相比具有更优越的性能。

英文摘要:

Face multi-attribute prediction benefits substantially from multi-task learning (MTL), which learns multiple face attributes simultaneously to achieve shared or mutually related representations of different attributes. The most widely used MTL convolutional neural network is heuristically or empirically designed by sharing all of the convolutional layers and splitting at the fully connected layers for task-specific losses. However, it is improper to view all low and mid-level features for different attributes as being the same, especially when these attributes are only loosely related. In this paper, we propose a novel multi-attribute tensor correlation neural network (MTCN) for face attribute prediction. The structure shares the information in low-level features (e.g., the first two convolutional layers) but splits that in high-level features (e.g., from the third convolutional layer to the fully connected layer). At the same time, during high-level feature extraction, each subnetwork (e.g., Age-Net, Gender-Net, ..., and Smile-Net) excavates closely related features from other networks to enhance its features. Then, we project the features of the C9 layers of the fine-tuned subnetworks into a highly correlated space by using a novel tensor correlation analysis algorithm (NTCCA). The final face attribute prediction is made based on the correlation matrix. Experimental results on benchmarks with multiple face attributes (CelebA and LFWA) show that the proposed approach has superior performance compared to state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑