Abstract

Given a collection of images containing a common object, we seek to learn a model for the object without the use of bounding boxes or segmentation masks. In linguistics, a single document provides no information about location of the topics it contains. On the contrary, an image has a lot to tell us about where foreground and background topics lie. Extensive literature on modelling bottom-up saliency and pop-out aims at predicting eye fixations and allocation of visual attention in a single image, prior to any recognition of content. Most salient image parts are likely to capture image foreground. We propose a novel proba- bilistic model, shape and figure-ground aware model (sFGmodel) that exploits bottom-up image saliency to compute an informative prior on segment topic as- signments. Our model exploits both figure-ground organization in each image separately, as well as feature re-occurrence across the image collection. Since we use image dependent topic prior, during model learning we optimize a condi- tional likelihood of the image collection given the image bottom-up saliency in- formation. Our discriminative framework can tolerate larger intraclass variability of objects with fewer training data. We iterate between bottom-up figure-ground image organization and model parameter learning by accumulating image statis- tics from the entire image collection. The model learned influences later image figure-ground labelling. We pr esent results of our approach on diverse datasets showing great improvement over generative probabilistic models that do not ex- ploit image saliency, indicating the suitability of our model for weakly-supervised visual organization.