Abstract

The success of an image classification algorithm largelydepends on how it incorporates local information in theglobal decision. Popular approaches such as average-pooling and max-pooling are suboptimal in many sit-uations. In this paper we propose Region RankingSVM (RRSVM), a novel method for pooling local informa-tion from multiple regions. RRSVM exploits the correlation of local regions in an image, and it jointly learns a region evaluation function and a scheme for integrating multiple regions. Experiments on PASCAL VOC 2007, VOC 2012, and ILSVRC2014 datasets show that RRSVM outperforms the methods that use the same feature type and extract features from the same set of local regions. RRSVM achievessimilar to or better than the state-of-the-art performance onall datasets.