Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Discovering Objects and their Localization in Images
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Unsupervised Learning of Categories from Sets of Partially Matching Image Features
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
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
PatchMatch: a randomized correspondence algorithm for structural image editing
ACM SIGGRAPH 2009 papers
Foreground Focus: Unsupervised Learning from Partially Matching Images
International Journal of Computer Vision
From a set of shapes to object discovery
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Optimizing color consistency in photo collections
ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
| Hi-index | 0.00 |
We define a "good image cluster" as one in which images can be easily composed (like a puzzle) using pieces from each other, while are difficult to compose from images outside the cluster. The larger and more statistically significant the pieces are, the stronger the affinity between the images. This gives rise to unsupervised discovery of very challenging image categories. We further show how multiple images can be composed from each other simultaneously and efficiently using a collaborative randomized search algorithm. This collaborative process exploits the "wisdom of crowds of images", to obtain a sparse yet meaningful set of image affinities, and in time which is almost linear in the size of the image collection. "Clustering-by-Composition" can be applied to very few images (where a 'cluster model' cannot be 'learned'), as well as on benchmark evaluation datasets, and yields state-of-the-art results.