.png){kind=icon}
返回
Sparse deep feature learning for facial expression recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2019.106966.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
While weight sparseness-based regularization has been used to learn better deep features for image recognition problems, it introduced a large number of variables for optimization and can easily converge to a local optimum. The L2-norm regularization proposed for face recognition reduces the impact of the noisy information, while expression information is also suppressed during the regularization. A feature sparseness-based regularization that learns deep features with better generalization capability is proposed in this paper. The regularization is integrated into the loss function and optimized with a deep metric learning framework. Through a toy example, it is showed that a simple network with the proposed sparseness outperforms the one with the L2-norm regularization. Furthermore, the proposed approach achieved competitive performances on four publicly available datasets, i.e., FER2013, CK+, Oulu-CASIA and MMI. The state-of-the-art cross-database performances also justify the generalization capability of the proposed approach. (C) 2019 Elsevier Ltd. All rights reserved.
Keyword:
Expression recognition
Feature sparseness
Deep metric learning
Fine tuning
Generalization capability
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:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Deep cross residual network for HEp-2 cell staining pattern classification用于HEp-2细胞染色模式分类的深度交叉残差网络.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Facial Expression Recognition Based on Deep Evolutional Spatial-Temporal Networks基于深度演化时空网络的人脸表情识别
OAAI
OAAI分享收藏Dynamic Facial Expression Recognition With Atlas Construction and Sparse Representation基于图谱构建和稀疏表示的动态人脸表情识别
PREAI
分享收藏分享收藏Handbook of Research on Social Marketing and Its Influence on Animal Origin Food Product Consumption
PREAI
分享收藏
查看更多内容