Method for improving zero-shot image classification

The Journal of Engineering

Mengyao Lv¹  Xiangfeng Chen²  Chong Zhang³  Wenbai Chen⁴ 

[1] Technology University , Beijing , People'MOE Key Laboratory of Machine Perception , Beijing , People'School of Automation Beijing Information Science &s Republic of China

关键词: mapping matrix;    zero-shot image classification;    metric function;    Pearson correlation coefficient;    training dataset;    visual space;    visual feature;    similarity metric method;    nearest neighbours;    semantic space;   

DOI  :  10.1049/joe.2018.8292

学科分类：工程和技术（综合）

来源: IET

【 摘 要 】

In order to improve the robustness of the similarity metric method of image classification, and reduce the complexity of the measure function, the Pearson correlation coefficient is introduced to improve the zero-shot image classification. Firstly, the mapping matrix from visual space to semantic space is learned by the training dataset, and the visual feature is aligned by it. Then in the semantic space, the similarity between features is calculated by the metric function, predicting the label of unseen class by the nearest neighbours. Experiments show that zero-shot image classification based on Pearson correlation coefficient is better than Euclidean distance and cosine similarity.

【 授权许可】

CC BY