LOCUS: Learning Object Classes with Unsupervised Segmentation
- π€ Speaker: John Winn, Microsoft Research
- π Date & Time: Wednesday 22 June 2005, 15:00 - 16:00
- π Venue: Ryle Seminar Room, Cavendish Laboratory
Abstract
LOCUS (Learning Object Classes with Unsupervised Segmentation) is a system for learning object class models and object segmentations from unannotated images. LOCUS 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 the model is that the object appearance is allowed to vary from image to image, allowing for significant within-class variation.
I will show that LOCUS successfully learns class models from unlabelled images, whilst also giving segmentation accuracies that rival existing supervised segmentation methods. LOCUS also infers the position and pose of the object in each image.
The intention is to use these class models for simultaneous recognition and segmentation of objects. I will present some preliminary results for this task and discuss some promising extensions to the LOCUS model. Finally, I will demonstrate that LOCUS can be used to perform motion segmentation and object tracking in video, despite changes in illumination, pose and background clutter.
This is joint work with Nebojsa Jojic of MSR Redmond
Series This talk is part of the Inference Group series.
Included in Lists
- All Cavendish Laboratory Seminars
- All Talks (aka the CURE list)
- Biology
- Cambridge Neuroscience Seminars
- Cambridge talks
- Centre for Health Leadership and Enterprise
- Chris Davis' list
- dh539
- dh539
- Featured lists
- Guy Emerson's list
- Hanchen DaDaDash
- Inference Group
- Inference Group Summary
- Interested Talks
- Joint Machine Learning Seminars
- Life Science
- Life Sciences
- Machine Learning Summary
- ME Seminar
- ML
- Neurons, Fake News, DNA and your iPhone: The Mathematics of Information
- Neuroscience
- Neuroscience Seminars
- Neuroscience Seminars
- Required lists for MLG
- rp587
- Ryle Seminar Room, Cavendish Laboratory
- School of Physical Sciences
- Stem Cells & Regenerative Medicine
- Thin Film Magnetic Talks
- yk373's list
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)

John Winn, Microsoft Research
Wednesday 22 June 2005, 15:00-16:00