Learning semantic kernels for scene classification

Lei Zhang, Xiantong Zhen, Jiqing Han, Xuezhi Xiang

Abstract: In this paper we propose to learn semantic kernels for scene classification. We first decompose the Object Bank representation into subspaces associated with each object, Anchor Objects are then created by clustering for each scene class separately. The Anchor Distances are computed to measure the distance between objects to scene classes. In order to take the advantage of the discriminative information from different scene classes, we propose semantic kernels based on the anchor distances to different classes for scene classification. Through extensive experiments on two benchmark datasets: UIUC-Sports dataset and 15-Scene dataset, we prove that the proposed Semantic Kernels can significantly improve the original Object Bank and achieve state-of-the-art performance.