Image retrieval based on image-to-class similarity

Similar image/shape retrieval has attractedincreasing interests in recent years. A typical strategy of existing retrieval algorithms is to rank the images according to the image-to-image similarities, e.g., the similarities between the query image and the images in the database. This strategy ignores the inherent information of the class that the query image belongs to (we call it query class). To address this issue, rather than using image-to-image similarity, we propose a simple yet effective retrieval method based on exploring the image-to-class similarity. The method uses an iterative framework, where the size of the query class is progressively enlarged according to the previous retrieval results, and the ranked list is generated according to the similarities between the images in the database and the query class. This framework enables us to explore the inherent information of the query class, and hence helps to improve the retrieval accuracy. Experimental results on various datasets demonstrate that our method is able to effectively improve the image and shape retrieval accuracy compared to state-of-the-art methods.