Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Class-Specific, Top-Down Segmentation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
Generalizing Swendsen-Wang to Sampling Arbitrary Posterior Probabilities
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
A Min-Cover Approach for Finding Salient Curves
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Multiscale Categorical Object Recognition Using Contour Fragments
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised Category Modeling, Recognition, and Segmentation in Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Object detection by contour segment networks
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Weakly Supervised Localization and Learning with Generic Knowledge
International Journal of Computer Vision
Connecting missing links: object discovery from sparse observations using 5 million product images
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
"Clustering by composition": unsupervised discovery of image categories
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
| Hi-index | 0.00 |
This paper presents an approach to object discovery in a given unlabeled image set, based on mining repetitive spatial configurations of image contours. Contours that similarly deform from one image to another are viewed as collaborating, or, otherwise, conflicting. This is captured by a graph over all pairs of matching contours, whose maximum a posteriori multicoloring assignment is taken to represent the shapes of discovered objects. Multicoloring is conducted by our new Coordinate Ascent Swendsen-Wang cut (CASW). CASW uses the Metropolis-Hastings (MH) reversible jumps to probabilistically sample graph edges, and color nodes. CASW extends SW cut by introducing a regularization in the posterior of multicoloring assignments that prevents the MH jumps to arrive at trivial solutions. Also, CASW seeks to learn parameters of the posterior via maximizing a lower bound of the MH acceptance rate. This speeds up multicoloring iterations, and facilitates MH jumps from local minima. On benchmark datasets, we outperform all existing approaches to unsupervised object discovery.