Improving invariance in visual classification with biologically inspired mechanism
文献类型：期刊论文
| 作者 | Tang, Tang; Qiao, Hong
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2014-06-10 |
| 卷号 | 133页码:328-341 |
| 关键词 | Biologically inspired Visual classification Max-pooling Template matching |
| 英文摘要 | A computational model of visual cortex has raised great interest in developing algorithms mimicking human visual systems. The max-operation is employed in the model to emulate the scale and position invariant responses of the visual cells. We further extend this idea to enhance the tolerance of visual classification against the general intra-class variability. A general architecture of the basic block constituting the model is first presented. The architecture adaptively chooses the best matching template from a set of competing templates to predict the label of the incoming sample. To optimize the non-convex and non-smooth objective function resulted, we develop an algorithm to train each template alternately. Experiments show that the proposed method significantly outperforms linear classifiers as a template matching method in several image classification tasks, and is much more computationally efficient than other commonly used non-linear classifiers. In the image classification task on the Caltech 101 database, the performance of the biologically inspired model is obviously boosted by incorporating the proposed method. (C) 2014 Elsevier B.V. All rights reserved. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence |
| 研究领域[WOS] | Computer Science |
| 关键词[WOS] | OBJECT RECOGNITION ; FACE DETECTION ; RECEPTIVE-FIELDS ; BACK-PROPAGATION ; COMPUTER VISION ; FEATURES ; CORTEX |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000334481400032 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/3039]  |
| 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 | Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Tang, Tang,Qiao, Hong. Improving invariance in visual classification with biologically inspired mechanism[J]. NEUROCOMPUTING,2014,133:328-341. |
| APA | Tang, Tang,&Qiao, Hong.(2014).Improving invariance in visual classification with biologically inspired mechanism.NEUROCOMPUTING,133,328-341. |
| MLA | Tang, Tang,et al."Improving invariance in visual classification with biologically inspired mechanism".NEUROCOMPUTING 133(2014):328-341. |
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。