Unsupervised object category discovery via information bottleneck method

We present a novel approach to automatically discover object categories from a collection of unlabeled images. This is achieved by the Information Bottleneck method, which finds the optimal partitioning of the image collection by maximally preserving the relevant information with respect to the latent semantic residing in the image contents. In this method, the images are modeled by the Bag-of-Words representation, which naturally transforms each image into a visual document composed of visual words. Then the sIB algorithm is adopted to learn the object patterns by maximizing the semantic correlations between the images and their constructive visual words. Extensive experimental results on 15 benchmark image datasets show that the Information Bottleneck method is a promising technique for discovering the hidden semantic of images, and is superior to the state-of-the-art unsupervised object category discovery methods.