低秩约束的在线自监督学习的场景分类方法 | |
丛杨; 宋红玉; 唐延东 | |
2014-05-14 | |
专利国别 | 中国 |
专利号 | CN103793713A |
专利类型 | 发明 |
产权排序 | 1 |
权利人 | 中国科学院沈阳自动化研究所 |
其他题名 | Low-rank constraint online self-supervised learning scene classification method |
中文摘要 | 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。 |
是否PCT专利 | 否 |
英文摘要 | 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. |
申请日期 | 2012-10-31 |
语种 | 中文 |
专利申请号 | CN201210429630.1 |
专利代理 | 沈阳科苑专利商标代理有限公司 21002 |
内容类型 | 专利 |
源URL | [http://ir.sia.cn/handle/173321/15008] |
专题 | 沈阳自动化研究所_机器人学研究室 |
推荐引用方式 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. CN103793713A. 2014-05-14. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论