Efficient Category Mining by Leveraging Instance Retrieval

We focus on the problem of mining object categories from large datasets like Google Street View images. Mining object categories in these unannotated datasets is an important and useful step to extract meaningful information. Often the location and spatial extent of an object in an image is unknown. Mining objects in such a setting is hard. Recent methods model this problem as learning a separate classifier for each category. This is computationally expensive since a large number of classifiers are required to be trained and evaluated, before one can mine a concise set of meaningful objects. On the other hand, fast and efficient solutions have been proposed for the retrieval of instances (same object) from large databases. We borrow, from instance retrieval pipeline, its strengths and adapt it to speed up category mining. For this, we explore objects which are "near-instances". We mine several near-instance object categories from images. Using an instance retrieval based solution, we are able to mine certain categories of near-instance objects much faster than an Exemplar SVM based solution.