Object discovery by clustering correlated visual word sets

Abstract—This paper presents a novel approach to discov-ering particular objects from a set of unannotated images. We aim to find discriminative feature sets that can effectively represent particular object classes (as opposed to object cate-gories). We achieve this by mining correlated visual word sets from the bag-of-features model. Specifically, we consider that a visual word set belongs to the same object class if all its visual words consistently occur together in the same image. To efficiently find such sets we apply Min-LSH to the occurrence vector of the each visual word. An agglomerative hierarchical clustering is further performed to eliminate redundancy and obtain more representative sets. We also propose a simple and efficient strategy for quantizing the feature descriptors based on locality-sensitive hashing. By experiment, we show that our approach can efficiently discover objects against cluster and slight viewpoint variations. Keywords-hashing; Min-LSH; object discovery; correlated itemset mining; I