|
|
论文:2019,Vol:37,Issue(6):1271-1277 |
|
|
引用本文： |
|
|
陈雯柏, 陈祥凤, 刘琼, 韩琥. 一种粒子群优化融合特征的零样本图像分类算法[J]. 西北工业大学学报 |
|
|
CHEN Wenbai, CHEN Xiangfeng, LIU Qiong, HAN Hu. Zero-Shot Image Classification Algorithm Based on Particle Swarm Optimization Fusion Feature[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 一种粒子群优化融合特征的零样本图像分类算法 |
|
| 陈雯柏1, 陈祥凤1, 刘琼1, 韩琥2 |
|
1. 北京信息科技大学 自动化学院, 北京 100101;
2. 中国科学院计算技术研究所, 北京 100190 |
| 摘要: |
| 针对目标类语义属性描述的局限性，提出一种基于自适应加权融合特征的零样本图像分类算法。首先，随机初始化融合权重，利用神经网络融合文本的语义词向量特征和语义属性；然后，利用粒子群算法优化特征融合的权重；最后，把加权融合的特征作为零样本图像分类的迁移知识。实验结果表明，基于自适应加权融合的零样本图像分类算法在动物属性数据集（AWA）上测试的准确率达到88.9%，验证了该方法的有效性。同时与融合特征算法相比，亦提高了零样本图像分类模型的稳定性。 |
| 关键词:
自适应加权
融合特征
语义属性
语义词向量
零样本图像分类
|
|
| Zero-Shot Image Classification Algorithm Based on Particle Swarm Optimization Fusion Feature |
|
| CHEN Wenbai1, CHEN Xiangfeng1, LIU Qiong1, HAN Hu2 |
|
1. School of Automation, Beijing Information Science & Technology University, 100101, China;
2. Institute of Computing Technology, Chinese Academy of Science, 100190 China |
| Abstract: |
| Aiming at the limitation of describing the semantic attributes of target classification, this paper proposes an adaptive weighted fusion feature based zero-sampling image classification algorithm. Firstly, the fusion weights are initialized randomly. Meantime, the semantic vector features and semantic attributes of the text are fused by neural network. Then, particle swarm optimization algorithm is used to optimize the weight of feature fusion. Finally, the features of weighted fusion are regarded as the transfer knowledge of the classification of zero-sampling images. The experimental results show that the classification algorithm based on adaptive weighted fusion for the zero-sampling image has an accuracy rate of 88.9% on the Animals with Attributes (AWA) data set, which illustrates the effectiveness. What's more, the proposed algorithm also improves the stability of the classification model for the zero-sampling image compared with the fusion feature. |
| Key words:
adaptive weighting
fusion feature
semantic attribute
semantic word vector
zero-shot image classification
|
|
| 收稿日期: 2019-01-17
修回日期:
|
| DOI: 10.1051/jnwpu/20193761271 |
| 基金项目: 北京市自然科学基金（4202026）与2018年度北京市属高校青年拔尖人才培育项目（CIT&TCD201804054）资助 |
| 通讯作者:
Email： |
| 作者简介: 陈雯柏(1975-),北京信息科技大学教授、博士,主要从事智能检测与模式识别、传感器网络研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 陈雯柏 在本刊中的所有文章 |
| 陈祥凤 在本刊中的所有文章 |
| 刘琼 在本刊中的所有文章 |
| 韩琥 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] LAROCHELLE H, ERHAN D, BENGIO Y. Zero-Data Learning of New Tasks[C]//23rd AAAI Conference on Artificial Intelligence, 2008:646-651
[2] LAMPERT C H, NICKISCH H, HARMELING S. Attribute-Based Classification for Zero-Shot Visual Object Categorization[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2013, 36(3):453-465
[3] WANG D, LI Y, LIN Y, et al. Relational Knowledge Transfer for Zero-Shot Learning[C]//Thirtieth AAAI Conference on Artificial Intelligence, 2016:2145-2151
[4] YU J, WU S, WANG L, et al. Robust Zero-Shot Learning with Source Attributes Noise[C]//2016 International Conference on Progress in Informatics and Computing, 2016:205-209
[5] WANG L, WU S, YU J, et al. Learning Discriminative Instance Attribute for Zero-Shot Classification[C]//2016 International Conference on Progress in Informatics and Computing, 2016:210-213
[6] CHENG Y, QIAO X, WANG X, et al. Random Forest Classifier for Zero-Shot Learning Based on Relative Attribute[J]. IEEE Trans on Neural Networks, 2018, 29(5):1662-1674
[7] WANG S, JIANG S, HUANG Q, et al. S3MKL:Scalable Semi-Supervised Multiple Kernel Learning for Image Data Mining[C]//Proceedings of the 18th ACM International Conference on Multimedia, 2010:163-172
[8] SOCHER R, GANJOO M, MANNING C D, et al. Zero-Shot Learning Through Cross-Modal Transfer[C]//Advances in Neural Information Processing Systems, 2013:935-943
[9] LI Y, WANG D, HU H, et al. Zero-Shot Recognition Using Dual Visual-Semantic Mapping Paths[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017:3279-3287
[10] KODIROV E, XIANG T, GONG S. Semantic Autoencoder for Zero-Shot Learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017:3174-3183
[11] ZHANG L, XIANG T, GONG S. Learning a Deep Embedding Model for Zero-Shot Learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017:2021-2030
[12] FROME A, CORRADO G S, SHLENS J, et al. Devise:a Deep Visual-Semantic Embedding Model[C]//Advances in Neural Information Processing Systems, 2013:2121-2129
[13] YANG Y, HOSPEDALES T M. A Unified Perspective on Multi-Domain and Multi-Task Learning[J/OL](2015-03-26)[2019-09-17]. https://arxiv.org/bas/1412.7489,2014
[14] JIMMY BA Lei, SWERSKY K, FIDLER S. Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015:4247-4255 |
|
|
|
|
|
|
|
