| 低秩约束的在线自监督学习的场景分类方法 | |
| Alternative Title | Low-rank constraint online self-supervised learning scene classification method |
丛杨 ; 宋红玉; 唐延东
| |
| Department | 机器人学研究室 |
| Rights Holder | 中国科学院沈阳自动化研究所 |
| Patent Agent | 沈阳科苑专利商标代理有限公司 21002 |
| Country | 中国 |
| Subtype | 发明 |
| Status | 有权 |
| Abstract | 本发明涉及低秩约束的在线自监督学习的场景分类方法，包括以下步骤：对离线的图像数据进行训练并进行特征提取；进行小批训练来获得一个最初的度量学习者；依次输入在线数据图像并提取图像特征；判断图像特征有无标签；如果有标签，则更新度量学习者；如果无标签，则测量图像特征与每个训练样本之间的相似度，利用生成的双向线性图来传播它的标签；判断样本的特征向量相似度得分；如果得分高则更新度量学习者；否则输入在线数据图像。本发明能够逐渐地实现自我更新并且合并从标记样本和未标记样本获得的有用信息；用统一的在线自我更新模型的框架用来处理在线场景分类，能够实现场景的在线自动分类，保证了分类的准确性，提高了工作效率。 |
| Other Abstract | The invention relates to a low-rank constraint online self-supervised learning scene classification method. The method comprises the following steps: performing training and feature extraction on off-line image data; carrying out small-batch training to obtain an initial metric learner; inputting online data images sequentially and extracting image features; judging whether each image feature has a label; if the image feature has the label, updating the metric learner; if the image feature has no label, measuring the similarity between the image feature and each training sample, and utilizing a generated bidirectional linear graph to transmit the label; judging feature vector similarity scores of the sample; if the scores are high, updating the metric learner; and otherwise, inputting online data images. According to the scene classification method, self-updating can be realized gradually and useful information obtained from marked samples and unmarked samples can be combined; and the framework of a unified on-line self-updating model is utilized to process online scene classification, so that the on-line automatic scene classification can be achieved, the accuracy of classification is ensured, and work efficiency is improved. |
| PCT Attributes | 否 |
| Application Date | 2012-10-31 |
| 2014-05-14 | |
| Date Available | 2017-09-15 |
| Application Number | CN201210429630.1 |
| Open (Notice) Number | CN103793713A |
| Language | 中文 |
| Contribution Rank | 1 |
| Document Type | 专利 |
| Identifier | http://ir.sia.cn/handle/173321/15008 |
| Collection | 机器人学研究室 |
| Affiliation | 中国科学院沈阳自动化研究所 |
| Recommended Citation GB/T 7714 | 丛杨,宋红玉,唐延东. 低秩约束的在线自监督学习的场景分类方法[P]. 2014-05-14. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment