Enhanced HMAX model with feedforward feature learning for multiclass categorization
文献类型：期刊论文
| 作者 | Li, Yinlin1 ; Wu, Wei1; Zhang, Bo2; Li, Fengfu2
|
| 刊名 | FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
 |
| 出版日期 | 2015-10-07 |
| 卷号 | 9页码:1-14 |
| 关键词 | HMAX biologically inspired feedforward saliency map middle level patch learning feature encoding multiclass categorization |
| 英文摘要 | 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. |
| WOS标题词 | Science & Technology ; Life Sciences & Biomedicine |
| 类目[WOS] | Mathematical & Computational Biology ; Neurosciences |
| 研究领域[WOS] | Mathematical & Computational Biology ; Neurosciences & Neurology |
| 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记录号 | WOS:000362659000001 |
| 公开日期 | 2016-05-03 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/10730]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 |
| 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。