.png){kind=icon}
返回
Improved curriculum learning using SSM for facial expression recognition
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-019-01759-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Facial expression recognition is an important research issue in the pattern recognition field. However, the generalization of the model still remains a challenging task. In this paper, we apply a strategy of curriculum learning to facial expression recognition during the stage of training. And a novel curriculum design method is proposed. The system first employs the unsupervised density-distance clustering method to determine the clustering center of each category. Then, the dataset is divided into three subsets of various complexity according to the distance from each sample to the clustering center in the feature space. Importantly, we develop a multistage training process where a main model is trained by continuously adding harder samples to training set to increase the complexity. To solve the problem that the model has a poor recognition accuracy for anger, fear and sadness, a self-selection mechanism is introduced in the test stage to make further judgment on the result of the main model. Experiment results indicate that the proposed model can achieve a satisfactory recognition accuracy of 72.11% on FER-2013 and 98.18% on CK+ dataset for 7-class facial expressions, which outperforms the other state-of-the-art methods.
Keyword:
Curriculum learning
Density-distance clustering
Facial expression
Recognition
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
.png){kind=icon}
分享收藏分享收藏分享收藏Prevalence of DSM-IV Major Depression Among U.S. Military Personnel: Meta-Analysis and Simulation
OAAI
OAAI分享收藏A case of chronic disseminated lupus erythematosus in a psoriatic patient receiving ustekinumab
PREAI
分享收藏
查看更多内容