Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation

Z. Shi, T. M. Hospedales, T. Xiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We address the problem of localisation of objects as bounding boxes in images with weak labels. This weakly supervised object localisation problem has been tackled in the past using discriminative models where each object class is localised independently from other classes. We propose a novel framework based on Bayesian joint topic modelling. Our framework has three distinctive advantages over previous works: (1) All object classes and image backgrounds are modelled jointly together in a single generative model so that "explaining away" inference can resolve ambiguity and lead to better learning and localisation. (2) The Bayesian formulation of the model enables easy integration of prior knowledge about object appearance to compensate for limited supervision. (3) Our model can be learned with a mixture of weakly labelled and unlabelled data, allowing the large volume of unlabelled images on the Internet to be exploited for learning. Extensive experiments on the challenging VOC dataset demonstrate that our approach outperforms the state-of-the-art competitors.
Original languageEnglish
Title of host publication2013 IEEE International Conference on Computer Vision
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2984-2991
Number of pages8
ISBN (Print)978-1-4799-2840-8
DOIs
Publication statusPublished - 1 Dec 2013

Fingerprint Dive into the research topics of 'Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation'. Together they form a unique fingerprint.

Cite this