Name
Abstract | ||
|---|---|---|
We propose a novel method for unsupervised class segmentation on a set of images. It alternates between segmenting object
instances and learning a class model. The method is based on a segmentation energy defined over all images at the same time,
which can be optimized efficiently by techniques used before in interactive segmentation. Over iterations, our method progressively
learns a class model by integrating observations over all images. In addition to appearance, this model captures the location
and shape of the class with respect to an automatically determined coordinate frame common across images. This frame allows
us to build stronger shape and location models, similar to those used in object class detection. Our method is inspired by
interactive segmentation methods [1], but it is fully automatic and learns models characteristic for the object class rather
than specific to one particular object/image. We experimentally demonstrate on the Caltech4, Caltech101, and Weizmann horses
datasets that our method (a) transfers class knowledge across images and this improves results compared to segmenting every
image independently; (b) outperforms Grabcut [1] for the task of unsupervised segmentation; (c) offers competitive performance
compared to the state-of-the-art in unsupervised segmentation and in particular it outperforms the topic model [2].
|
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-15555-0_28 | European Conference on Computer Vision |
Keywords | Field | DocType |
segmentation energy,unsupervised class segmentation,novel method,unsupervised segmentation,interactive segmentation,transfers class knowledge,interactive segmentation method,class model,object class detection,object class | Scale-space segmentation,Computer science,GrabCut,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Computer vision,Object-class detection,Pattern recognition,Segmentation,Active appearance model,Topic model,Machine learning | Conference |
Volume | ISSN | ISBN |
6315 | 0302-9743 | 3-642-15554-5 |
Citations | PageRank | References |
838 | 30.21 | 23 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bogdan Alexe | 1 | 1706 | 78.66 |
| Thomas Deselaers | 2 | 3569 | 203.12 |
| Vittorio Ferrari | 3 | 5369 | 284.83 |