Knowledge Commons of Institute of Automation,CAS
Improving Image Classification Performance with Automatically Hierarchical Label Clustering | |
Chen, Zhiqiang1,2; Du, Changde1,2; Huang, Lijie1; Li, Dan1,2; He,Huiguang1,2,3 | |
2018-08 | |
会议名称 | 2018 24th International Conference on Pattern Recognition (ICPR) |
会议录名称 | 2018 24th International Conference on Pattern Recognition (ICPR) |
卷号 | 无 |
期号 | 无 |
页码 | 无 |
会议日期 | 2018-8 |
会议地点 | Beiing, China |
会议举办国 | China |
会议录编者/会议主办者 | 无 |
出版地 | 无 |
出版者 | 无 |
摘要 | Image classification is a common and foundational problem in computer vision. In traditional image classification, a category is assigned with single label, which is difficult for networks to learn better features. On the contrary, hierarchical labels can depict the structure of categories better, which helps network to learn more hierarchical features and improve the classification performance. Though many datasets contain images with multi-labels, the labels in these datasets usually lack of hierarchy. To overcome this problem, we propose a new method to improve image classification performance with Automatically Hierarchical Label Clustering (AHLC). Firstly, AHLC calculates the similarity between each pair of original categories by how easily they are misclassified with a pre-trained classifier. Secondly, AHLC obtains hierarchical labels by merging similar categories using hierarchical clustering. Finally, AHLC trains a new classifier with hierarchial labels to improve the original classification performance. We evaluate our method on MNIST and CIFAR100 datasets and the results demonstrate the superiority of our method. The main contribution of this work is that we can simply improve an existing classification network by AHLC without extra information or heavy architecture redesign. |
关键词 | classification,deep neural network, label clustering |
学科门类 | 工学 ; 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 无 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42216 |
专题 | 脑图谱与类脑智能实验室_神经计算与脑机交互 |
作者单位 | 1.Research Center for Brain-inspired Intelligence and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.University of Chinese Academy of Sciences, Beijing, China 3.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Chen, Zhiqiang,Du, Changde,Huang, Lijie,et al. Improving Image Classification Performance with Automatically Hierarchical Label Clustering[C]//无. 无:无,2018:无. |
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 | ||
ICPR18_0541_FI1.pdf(2034KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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