Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning
Qiao, Hong1; Li, Yinlin1; Li, Fengfu2; Xi, Xuanyang1; Wu, Wei1
2016-10-01
发表期刊IEEE TRANSACTIONS ON CYBERNETICS
卷号46期号:10页码:2335-2347
文章类型Article
摘要Recently, many biologically inspired visual computational models have been proposed. The design of these models follows the related biological mechanisms and structures, and these models provide new solutions for visual recognition tasks. In this paper, based on the recent biological evidence, we propose a framework to mimic the active and dynamic learning and recognition process of the primate visual cortex. From principle point of view, the main contributions are that the framework can achieve unsupervised learning of episodic features (including key components and their spatial relations) and semantic features (semantic descriptions of the key components), which support higher level cognition of an object. From performance point of view, the advantages of the framework are as follows: 1) learning episodic features without supervision-for a class of objects without a prior knowledge, the key components, their spatial relations and cover regions can be learned automatically through a deep neural network (DNN); 2) learning semantic features based on episodic features-within the cover regions of the key components, the semantic geometrical values of these components can be computed based on contour detection; 3) forming the general knowledge of a class of objects-the general knowledge of a class of objects can be formed, mainly including the key components, their spatial relations and average semantic values, which is a concise description of the class; and 4) achieving higher level cognition and dynamic updating-for a test image, the model can achieve classification and subclass semantic descriptions. And the test samples with high confidence are selected to dynamically update the whole model. Experiments are conducted on face images, and a good performance is achieved in each layer of the DNN and the semantic description learning process. Furthermore, the model can be generalized to recognition tasks of other objects with learning ability.
关键词Biologically Inspired Hierarchical Model Key Components Learning Semantic Description
WOS标题词Science & Technology ; Technology
学科领域模式识别与智能系统
DOI10.1109/TCYB.2015.2476706
关键词[WOS]EXTERNAL FEATURES ; OBJECT RECOGNITION ; UNFAMILIAR FACES ; PERCEPTION ; CORTEX ; IDENTIFICATION ; PROSOPAGNOSIA ; ADAPTATION ; MECHANISMS ; KNOWLEDGE
收录类别SCI ; SSCI
语种英语
项目资助者National Natural Science Foundation of China(61210009)
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号WOS:000384265600004
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/11640
专题复杂系统管理与控制国家重点实验室_机器人理论与应用
通讯作者Qiao, Hong
作者单位1.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Acad Math & Syst Sci, Inst Appl Math, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Qiao, Hong,Li, Yinlin,Li, Fengfu,et al. Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning[J]. IEEE TRANSACTIONS ON CYBERNETICS,2016,46(10):2335-2347.
APA Qiao, Hong,Li, Yinlin,Li, Fengfu,Xi, Xuanyang,&Wu, Wei.(2016).Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning.IEEE TRANSACTIONS ON CYBERNETICS,46(10),2335-2347.
MLA Qiao, Hong,et al."Biologically Inspired Model for Visual Cognition Achieving Unsupervised Episodic and Semantic Feature Learning".IEEE TRANSACTIONS ON CYBERNETICS 46.10(2016):2335-2347.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
tp3.pdf(2781KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Qiao, Hong]的文章
[Li, Yinlin]的文章
[Li, Fengfu]的文章
百度学术
百度学术中相似的文章
[Qiao, Hong]的文章
[Li, Yinlin]的文章
[Li, Fengfu]的文章
必应学术
必应学术中相似的文章
[Qiao, Hong]的文章
[Li, Yinlin]的文章
[Li, Fengfu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: tp3.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。