Volume 37, Number 6, December 2019
|Page(s)||1271 - 1277|
|Published online||11 February 2020|
Zero-Shot Image Classification Algorithm Based on Particle Swarm Optimization Fusion Feature
School of Automation, Beijing Information Science & Technology University, 100101, China
2 Institute of Computing Technology, Chinese Academy of Science, 100190 China
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
关键字 : 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
© 2019 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.