Semi-supervised learning based on intra-view heterogeneity and inter-view compatibility for image classification

To achieve high value of classification results by using a limited number of training samples, designing a multi-view semi-supervised classification model is extremely urgent. Moreover, considering that graph learning can fully capture the complex data structure information, we propose a graph-based multi-view semi-supervised classification approach named as Semi-supervised Classification based on Intra-view Heterogeneity and Inter-view Compatibility (SSC_IHIC). Specifically, the similarity between two samples can be measured based on the Euclidean distance. Considering that heterogeneity exists in intra-view sub-features, hence, the weights are learned adaptively. Besides, based on the inter-view compatibility, the consensus similarity graph is constructed on which the labels are propagated. To verify the effectiveness, the proposed approach is conducted on four data sets including MSRC-v1, Handwritten (HW), Cal101-7 and Cal101-20. From the experimental results, we can see that the classification performance about proposed method outperforms the single view classification methods and the state-of-the-art multi-view classification methods.