Semi-supervised multi-view binary learning for large-scale image clustering

Large-scale image clustering has attracted sustained attention in machine learning. The traditional methods based on real value representation often suffer from the data storage and calculation. To deal with these problems, the methods based on the binary representation and the multi-view learning are introduced recently. However, how to improve the clustering performance is still a challenge. Considering that one can obtain in prior parts of labels in many cases, we further develop the label information in the multi-view binary learning. This information is beneficial to the design of the involved similarity matrix, which plays an important part in the clustering problem. As a result, a new method is proposed, i.e., Semi-supervised Multi-view Binary Learning(SMBL). It is tested by using four benchmark data sets and compared with several commonly used large-scale and semi-supervised clustering approaches. The extensive experimental results show that the proposed method achieves superior performance.