LOCUS: learning object classes with unsupervised segmentation
John Michael Winn, Nebojša Jojić · 2005
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.
Cited by 520 works. doi:10.1109/iccv.2005.148
Authors
References
- Object class recognition by unsupervised scale-invariant learning
- Active Shape Models-Their Training and Application
- An Introduction to Variational Methods for Graphical Models
- "GrabCut"
- Feature extraction from faces using deformable templates
- What energy functions can be minimized via graph cuts?
- Combined Object Categorization and Segmentation With An Implicit Shape Model
- "GrabCut"
- Fast approximate energy minimization via graph cuts
- Combining Top-Down and Bottom-Up Segmentation