LOCUS: learning object classes with unsupervised segmentation
- 1 January 2005
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 756-763 Vol. 1
- https://doi.org/10.1109/iccv.2005.148
Abstract
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.Keywords
This publication has 13 references indexed in Scilit:
- Learning flexible sprites in video layersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Capturing image structure with probabilistic index mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- What energy functions can be minimized via graph cuts?Ieee Transactions On Pattern Analysis and Machine Intelligence, 2004
- Greedy Learning of Multiple Objects in Images Using Robust Statistics and Factorial LearningNeural Computation, 2004
- Object-specific figure-ground segregationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Object class recognition by unsupervised scale-invariant learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Fast approximate energy minimization via graph cutsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- An Introduction to Variational Methods for Graphical ModelsPublished by Springer Science and Business Media LLC ,1998
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- Feature extraction from faces using deformable templatesInternational Journal of Computer Vision, 1992