arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07563cs.CVcs.LGeess.IV
收藏

BPLF:一种基于情感集图像的人脸表情生成的双并行线性流模型

BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images

Chongqing University of Posts and Telecommunications(重庆邮电大学);Southwestern University of Finance and Economics(西南财经大学)

Gao Xu, Yuanpeng Long, Siwei Liu, Lijia Yang, Shimei Xu, Xiaoming Yao, Kunxian Shu

摘要:

基于流的生成模型是一种深度学习生成模型,它通过显式学习数据分布来获得生成数据的能力。从理论上讲,它的数据恢复能力比其他生成模型更强。但其实现存在模型设计有限、模型参数过多、计算繁琐等局限性。本文构造了一种用于从情感集图像生成人脸情感的双并行线性流模型,并在模型的表达能力和训练收敛速度方面进行了一系列改进。该模型主要由多个耦合层叠加构成多尺度结构,其中每个耦合层包含1*1可逆卷积和线性运算模块。此外,本文还对目前公开的人脸情感图像数据集进行了整理,提出了一种新的情感数据集,并通过该数据集对模型进行了验证。实验结果表明,在传统的卷积神经网络下,3层3*3卷积核更有利于人脸图像的特征提取。主成分分解的引入可以提高模型的收敛速度。

英文摘要:

The flow-based generative model is a deep learning generative model, which obtains the ability to generate data by explicitly learning the data distribution. Theoretically its ability to restore data is stronger than other generative models. However, its implementation has many limitations, including limited model design, too many model parameters and tedious calculation. In this paper, a bi-parallel linear flow model for facial emotion generation from emotion set images is constructed, and a series of improvements have been made in terms of the expression ability of the model and the convergence speed in training. The model is mainly composed of several coupling layers superimposed to form a multi-scale structure, in which each coupling layer contains 1*1 reversible convolution and linear operation modules. Furthermore, this paper sorted out the current public data set of facial emotion images, made a new emotion data, and verified the model through this data set. The experimental results show that, under the traditional convolutional neural network, the 3-layer 3*3 convolution kernel is more conducive to extracte the features of the face images. The introduction of principal component decomposition can improve the convergence speed of the model.

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。

↑