文章基本信息

标题：Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling
本地全文：下载
作者：Takayoshi Yamashita ; Takaya Nakamura ; Hiroshi Fukui 等
期刊名称：Information and Media Technologies
电子版ISSN：1881-0896
出版年度：2015
卷号：10
期号：3
页码：488-492
DOI：10.11185/imt.10.488
出版社：Information and Media Technologies Editorial Board
摘要：Facial part labeling which is parsing semantic components enables high-level facial image analysis, and contributes greatly to face recognition, expression recognition, animation, and synthesis. In this paper, we propose a cost-alleviative learning method that uses a weighted cost function to improve the performance of certain classes during facial part labeling. As the conventional cost function handles the error in all classes equally, the error in a class with a slightly biased prior probability tends not to be propagated. The weighted cost function enables the training coefficient for each class to be adjusted. In addition, the boundaries of each class may be recognized after fewer iterations, which will improve the performance. In facial part labeling, the recognition performance of the eye class can be significantly improved using cost-alleviative learning.
关键词：facial part labeling;cost-alleviative learning;convolutional neural network;cost-function;back propagation