| 基于粒子群算法寻最优属性关联下的零样本语义自编码器 |
| |
| 引用本文： | 芦楠楠, 张欣茹, 欧倪. 基于粒子群算法寻最优属性关联下的零样本语义自编码器[J]. 电子与信息学报, 2021, 43(4): 982-991. doi: 10.11999/JEIT200419 |
| |
| 作者姓名： | 芦楠楠 张欣茹 欧倪 |
| |
| 作者单位： | 1.中国矿业大学信息与控制工程学院 徐州 221116;;2.北京理工大学信息与电子学院 北京 100081;;3.北京理工大学自动化学院 北京 100081 |
| |
| 基金项目： | 国家自然科学基金(62006233, 51734009, U1710120, 51504241),国家重点研发计划(2019YFE0118500) |
| |
| 摘 要： | 针对零样本图像分类构建共享属性层时造成的信息缺失问题,该文提出一种嵌入属性关联性的补偿方法。通过语义自编码器构建特征到属性的映射,然后以最大后验概率估计在类高斯模型构建的基础上实现零样本图像分类。为弥补SAE对属性关系学习的不足,引入加性因子与乘性因子对属性相关性进行嵌入,并利用粒子群算法搜寻最优的因子参数,实现属性相...
|
| 关 键 词： | 零样本图像分类 相对属性 语义自编码器 粒子群优化 属性关联 |
| 收稿时间： | 2020-05-29 |
| 修稿时间： | 2020-12-10 |
Zero-shot Learning by Semantic Autoencoder Based on Particle Swarm Optimization Algorithm for Attribute Correlation |
| |
| Nannan LU, Xinru ZHANG, Ni OU. Zero-shot Learning by Semantic Autoencoder Based on Particle Swarm Optimization Algorithm for Attribute Correlation[J]. Journal of Electronics & Information Technology, 2021, 43(4): 982-991. doi: 10.11999/JEIT200419 |
| |
| Authors: | Nannan LU Xinru ZHANG Ni OU |
| |
| Affiliation: | 1. School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China;;2. School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China;;3. School of Automation, Beijing Institute of Technology, Beijing 100081, China |
| |
| Abstract: | To deal with the problem of missing information caused by zero-shot image classification during building a shared attribute layer, a compensation method is proposed to embed the attribute correlation. The proposed zero-shot classification utilizes Semantic AautoEncoder (SAE) to realize the feature-to-attribute mapping, and the invisible images are classified using maximum posterior probability estimation based on the class Gaussian distribution model. In order to make up for the lack of attribute relationships in SAE learning, the additive and multiplicative factors are introduced to embed the attribute correlation. The particle swarm algorithm is used to search for the optimal factor parameters to achieve the compensation of attribute correlation information. Experimental results show that when the same mapping method is adopted, the classification performance of zero-shot image classification based on attribute correlation on Pubfig and OSR data sets is significantly improved compared with other methods. |
| |
| Keywords: | Zero-shot image classification Relative attribute SAE(Semantic AutoEncoder) PSO(Partial Swarm Optimization) Attribute correlation |
|
| 点击此处可从《电子与信息学报》浏览原始摘要信息 |
|
点击此处可从《电子与信息学报》下载全文 |
|
