Convolutional Neural Networks for Subjective Face Attributes

作者：

Highlights：

• A novel dataset of over 6000 images annotated for all four traits of interest

• The deployment of a crowd-sourced data collection regime for high level attributes

• The comparison of different deep learning architectures for abstract modeling

• A set of predictors that have high agreement with human annotators

摘要

•A novel dataset of over 6000 images annotated for all four traits of interest•The deployment of a crowd-sourced data collection regime for high level attributes•The comparison of different deep learning architectures for abstract modeling•A set of predictors that have high agreement with human annotators

论文关键词：Psychophysics,Face attributes,Convolutional neural networks

论文评审过程：Received 19 October 2017, Revised 15 May 2018, Accepted 21 June 2018, Available online 19 July 2018, Version of Record 8 August 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.06.010