Open AccessMethod for improving zero‐shot image classification
Author(s) -
Chen Xiangfeng,
Chen Wenbai,
Zhang Chong,
Lv Mengyao,
Han Hu
Publication year - 2018
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2018.8292
Subject(s) - pattern recognition (psychology) , artificial intelligence , euclidean distance , feature vector , k nearest neighbors algorithm , pearson product moment correlation coefficient , robustness (evolution) , mathematics , metric (unit) , computer science , similarity (geometry) , measure (data warehouse) , image (mathematics) , euclidean space , semantic space , similarity measure , euclidean geometry , data mining , statistics , pure mathematics , chemistry , operations management , economics , gene , geometry , biochemistry
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.