Abstract

The goal of this paper is to discover a set of discriminative patches which can serve as a fully unsupervised mid-level visual repre- sentation. The desired patches need to satisfy two requirements: 1) to be representative, they need to occur frequently enough in the visual world; 2) to be discriminative, they need to be different enough from the rest of the visual world. The patches could correspond to parts, ob jects, “visual phrases”, etc. but are not restricted to be any one of them. We pose this as an unsupervised discriminative clustering problem on a huge dataset of image patches. We use an iterative procedure which alternates between clustering and training discriminative classifiers, while applying careful cross-validation at each step to prevent overfitting. The paper ex- perimentally demonstrates the effectiveness of discriminative patches as an unsupervised mid-level visual representation, suggesting that it could be used in place of visual words for many tasks. Furthermore, discrim- inative patches can also be used in a supervised regime, such as scene classification, where they demonstrate state-of-the-art performance on the MIT Indoor-67 dataset.