Enhanced HMAX model with feedforward feature learning for multiclass categorization
Li, Yinlin1; Wu, Wei1; Zhang, Bo2; Li, Fengfu2
发表期刊FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
2015-10-07
卷号9页码:1-14
文章类型Article
摘要In recent years, the interdisciplinary research between neuroscience and computer vision has promoted the development in both fields. Many biologically inspired visual models are proposed, and among them, the Hierarchical Max-pooling model (HMAX) is a feedforward model mimicking the structures and functions of V1 to posterior inferotemporal (PIT) layer of the primate visual cortex, which could generate a series of position- and scale- invariant features. However, it could be improved with attention modulation and memory processing, which are two important properties of the primate visual cortex. Thus, in this paper, based on recent biological research on the primate visual cortex, we still mimic the first 100-150 ms of visual cognition to enhance the HMAX model, which mainly focuses on the unsupervised feedforward feature learning process. The main modifications are as follows: (1) To mimic the attention modulation mechanism of V1 layer, a bottom-up saliency map is computed in the Si layer of the HMAX model, which can support the initial feature extraction for memory processing; (2) To mimic the learning, clustering and short-term memory to long-term memory conversion abilities of V2 and IT, an unsupervised iterative clustering method is used to learn clusters with multiscale middle level patches, which are taken as long-term memory; (3) Inspired by the multiple feature encoding mode of the primate visual cortex, information including color, orientation, and spatial position are encoded in different layers of the HMAX model progressively. By adding a softmax layer at the top of the model, multiclass categorization experiments can be conducted, and the results on Caltech101 show that the enhanced model with a smaller memory size exhibits higher accuracy than the original HMAX model, and could also achieve better accuracy than other unsupervised feature learning methods in multiclass categorization task.
关键词Hmax Biologically Inspired Feedforward Saliency Map Middle Level Patch Learning Feature Encoding Multiclass Categorization
WOS标题词Science & Technology ; Life Sciences & Biomedicine
DOI10.3389/fncom.2015.00123
关键词[WOS]HUMAN EXTRASTRIATE CORTEX ; INFERIOR TEMPORAL CORTEX ; PRIMATE VISUAL-CORTEX ; OBJECT RECOGNITION ; RECEPTIVE FIELDS ; STRIATE CORTEX ; VISION ; DISCRIMINATION ; CLASSIFICATION ; CONNECTIONS
收录类别SCI ; SSCi
语种英语
WOS研究方向Mathematical & Computational Biology ; Neurosciences & Neurology
WOS类目Mathematical & Computational Biology ; Neurosciences
WOS记录号WOS:000362659000001
引用统计
被引频次:20[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/10730
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
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, Inst Appl Math, Acad Math & Syst Sci, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Li, Yinlin,Wu, Wei,Zhang, Bo,et al. Enhanced HMAX model with feedforward feature learning for multiclass categorization[J]. FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,2015,9:1-14.
APA Li, Yinlin,Wu, Wei,Zhang, Bo,&Li, Fengfu.(2015).Enhanced HMAX model with feedforward feature learning for multiclass categorization.FRONTIERS IN COMPUTATIONAL NEUROSCIENCE,9,1-14.
MLA Li, Yinlin,et al."Enhanced HMAX model with feedforward feature learning for multiclass categorization".FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 9(2015):1-14.
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
Frontiers-in-computa(3664KB)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
[Li, Yinlin]的文章
[Wu, Wei]的文章
[Zhang, Bo]的文章
百度学术
百度学术中相似的文章
[Li, Yinlin]的文章
[Wu, Wei]的文章
[Zhang, Bo]的文章
必应学术
必应学术中相似的文章
[Li, Yinlin]的文章
[Wu, Wei]的文章
[Zhang, Bo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Frontiers-in-computational-neuroscience.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。