Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images
We address the problem of localisation of objects as bounding boxes in images and videos 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. In this paper, a novel framework based on Bayesian joint topic modelling is proposed, which differs significantly from the existing ones in that: (1) All foreground object classes are modelled jointly in a single generative model that encodes multiple object co-existence so that "explaining away" inference can resolve ambiguity and lead to better learning and localisation. (2) Image backgrounds are shared across classes to better learn varying surroundings and "push out" objects of interest. (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. Moreover, the Bayesian formulation enables the exploitation of various types of prior knowledge to compensate for the limited supervision offered by weakly labelled data, as well as Bayesian domain adaptation for transfer learning. Extensive experiments on the PASCAL VOC, ImageNet and YouTube-Object videos datasets demonstrate the effectiveness of our Bayesian joint model for weakly supervised object localisation.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationObjectTransfer LearningSimilar Papers 제목 키워드 기반
Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation
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 objec…
ObjectWeakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images
In this paper we propose a reinforcement learning based weakly supervised system for localisation. We train a controller function to localise regions of interest within an image by introducing a novel reward definition t…
Multiple Instance LearningObjectRegion Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classification
The deployment of automated systems to diagnose diseases from medical images is challenged by the requirement to localise the diagnosed diseases to justify or explain the classification decision. This requirement is hard…
ClassificationGeneral ClassificationRegion ProposalSaliency DetectionSelf-supervised object detection from audio-visual correspondence
We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-…
Objectobject-detectionObject DetectionSound Source Localization+1SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours
Accurate tumour segmentation is vital for various targeted diagnostic and therapeutic procedures for cancer, e.g., planning biopsies or tumour ablations. Manual delineation is extremely labour-intensive, requiring substa…
DiagnosticSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation