| 面向多任务学习的改进十字绣网络在人脸美丽预测中的研究 |
| |
| 引用本文： | 甘俊英,白振峰,吴必诚,翟懿奎,何国辉,曾军英. 面向多任务学习的改进十字绣网络在人脸美丽预测中的研究[J]. 信号处理, 2021, 37(5): 825-834. DOI: 10.16798/j.issn.1003-0530.2021.05.016 |
| |
| 作者姓名： | 甘俊英 白振峰 吴必诚 翟懿奎 何国辉 曾军英 |
| |
| 作者单位： | 五邑大学智能制造学部 |
| |
| 基金项目： | 国家自然科学基金项目(61771347);广东省基础与应用基础研究基金(2019A1515010716);广东省普通高校基础研究与应用基础研究重点项目(2018KZDXM073) |
| |
| 摘 要： | 目前,人脸美丽预测研究面临模型泛化能力欠佳、数据量不足、以及易于过拟合等问题。十字绣网络(Cross-Stitch Network)通过激活多个网络,进行端到端的学习,自动决定共享层,但忽略了图像信息主次问题。因此,本文对十字绣网络进行改进,将其部分层网络更换为自注意力(Self-Attention)模块与长短时记忆(Long Short Term Memory,LSTM)模块,从而实现层与层之间、模块与模块之间的参数共享。首先,进行图像预处理,包括统一尺寸、人脸对齐、图像增强、归一化和图像剪裁等;其次,初始化构建的改进十字绣网络,并将层与层之间的共享称之为“微共享”,将模块与模块之间的共享称之为“模块共享”;最后,对训练模型进行测试。实验结果表明,采用改进十字绣网络,人脸美丽预测取得63.95%的准确率,高于常规方法最高准确率;为多任务学习提供了一种新思路。
|
| 关 键 词： | 改进十字绣网络 自注意力模块 长短时记忆模块 微共享 模块共享 |
| 收稿时间： | 2020-08-19 |
Research of Improved Cross-Stitch Network for Multi-task Learning in Facial Beauty Prediction |
| |
| Affiliation: | Department of Intelligent Manufacturing of Wuyi University |
| |
| Abstract: | At present,there exist the problems such as poor model generalization ability, insufficient data, and easy over-fitting in Facial Beauty Prediction research. The Cross-Stitch Network automatically determines the shared layer by activating multiple networks for end-to-end learning, but it ignores the issue of image information priority and is not conducive to Multi-task Learning to distinguish features. Therefore, this paper improves the Cross-Stitch Network, replacing part of its layer network with Self-Attention module and LSTM module, to realize the parameter sharing between layers and between modules. First, we perform image preprocessing, including uniform size, face alignment, image enhancement, normalization, and image cropping. Second, we initialize the constructed Improved Cross-Stitch Network, in which the sharing between layers is called "Micro-sharing" , and the sharing between modules is called "Module sharing". Finally, the trained model is tested. Experimental results show that by the Improved Cross-Stitch Network, the accuracy of Facial Beauty Prediction is as high as 63.95%, higher than the highest accuracy rate of 62.97% by conventional methods. Therefore, the Improved Cross-Stitch Network provides a new idea for Multi-task Learning. |
| |
| Keywords: | |
|
| 点击此处可从《信号处理》浏览原始摘要信息 |
|
点击此处可从《信号处理》下载免费的PDF全文 |
|
