We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (learning object classes with unsupervised segmentation) which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape and pose. A key aspect of this model is that the object appearance is allowed to vary from image to image, allowing for significant within-class variation. By iteratively updating the belief in the object's position, size, segmentation and pose, LOCUS avoids making hard decisions about any of these quantities and so allows for each to be refined at any stage. We show that LOCUS successfully learns an object class model from unlabeled images, whilst also giving segmentation accuracies that rival existing supervised methods. Finally, we demonstrate simultaneous recognition and segmentation in novel images using the learned models for a number of object classes, as well as unsupervised object discovery and tracking in video.
LOCUS: learning object classes with unsupervised segmentation
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 756-763 Vol. 1
2005-01-01
933969 byte
Conference paper
Electronic Resource
English
LOCUS: Learning Object Classes with Unsupervised Segmentation
British Library Conference Proceedings | 2005
|