BriefGPT.xyz
Feb, 2020
基于互联卷积神经网络的端到端人脸解析
End-to-End Face Parsing via Interlinked Convolutional Neural Networks
HTML
PDF
Zi Yin, Valentin Yiu, Xiaolin Hu, Liang Tang
TL;DR
提出了一种基于Spatial Transformer Network的end-to-end面部分割框架,称为STN-iCNN,通过在两个分离的训练阶段之间添加STN,将原始two-stage iCNN连接起来,从而显着提高了面部分割的准确性。
Abstract
face parsing
is an important
computer vision
task that requires accurate pixel segmentation of facial parts (such as eyes, nose, mouth, etc.), providing a basis for further face analysis, modification, and other
→