首页> 外文期刊>Neural computation >Replicating Neuroscience Observations on ML/MF and AM Face Patches by Deep Generative Model
【24h】

Replicating Neuroscience Observations on ML/MF and AM Face Patches by Deep Generative Model

机译:通过深度生成模型复制ML / MF和AM面部贴片的神经科学观察结果

获取原文
获取原文并翻译 | 示例
           

摘要

A recent Cell paper (Chang & Tsao, 2017) reports an interesting discovery. For the face stimuli generated by a pretrained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit a strong linear relationship with the shape variables and appearance variables of the AAM that generates the face stimuli. In this letter, we show that this behavior can be replicated by a deep generative model, the generator network, that assumes that the observed signals are generated by latent random variables via a top-down convolutional neural network. Specifically, we learn the generator network from the face images generated by a pretrained AAM model using a variational autoencoder, and we show that the inferred latent variables of the learned generator network have a strong linear relationship with the shape and appearance variables of the AAM model that generates the face images. Unlike the AAM model, which has an explicit shape model where the shape variables generate the control points or landmarks, the generator network has no such shape model and shape variables. Yet it can learn the shape knowledge in the sense that some of the latent variables of the learned generator network capture the shape variations in the face images generated by AAM.
机译:Cell的最新论文(Chang&Tsao,2017)报告了一个有趣的发现。对于由预先训练的活动外观模型(AAM)生成的面部刺激,负责人脸识别的灵长类大脑区域中神经元的响应与AAM的形状变量和外观变量具有很强的线性关系,而AAM的形状变量和外观变量面对刺激。在这封信中,我们表明可以通过深度生成模型(生成器网络)来复制此行为,该模型假定观察到的信号是通过自上而下的卷积神经网络由潜在随机变量生成的。具体而言,我们使用变分自编码器从预训练AAM模型生成的面部图像中学习生成器网络,并且我们证明,所学习生成器网络的推断潜变量与AAM模型的形状和外观变量具有很强的线性关系生成人脸图像。与具有显式形状模型(其中形状变量生成控制点或界标)的AAM模型不同,生成器网络没有此类形状模型和形状变量。然而,它可以从学习到的生成器网络的某些潜在变量捕获AAM生成的面部图像中的形状变化的意义上学习形状知识。

著录项

  • 来源
    《Neural computation》 |2019年第12期|2348-2367|共20页
  • 作者单位

    Univ Calif Los Angeles Dept Stat Los Angeles CA 90095 USA;

    Harbin Engn Univ Coll Automat Harbin 150001 Heilongjiang Peoples R China;

    Univ Southern Calif Dept Comp Sci Los Angeles CA 90089 USA;

  • 收录信息 美国《科学引文索引》(SCI);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号