• Publication
  • PrePrints
  • Abstract - "Clustering by Composition" - Unsupervised Discovery of Image Categories
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
"Clustering by Composition" - Unsupervised Discovery of Image Categories
PrePrint
ISSN: 0162-8828
Alon Faktor, The Weizmann Institute of Science, Rehovot
Michal Irani, The Weizmann Institute of Science, Rehovot
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" yields state-of-the-art results on current benchmark evaluation datasets. It further yields promising results on new challenging datasets, such as datasets with very few images (where a 'cluster model' cannot be 'learned' by current methods), and a subset of the PASCAL VOC dataset (with huge variability in scale and appearance).
Index Terms:
Object recognition,Clustering,Segmentation
Citation:
Alon Faktor, Michal Irani, ""Clustering by Composition" - Unsupervised Discovery of Image Categories," IEEE Transactions on Pattern Analysis and Machine Intelligence, 17 Dec. 2013. IEEE computer Society Digital Library. IEEE Computer Society, <http://doi.ieeecomputersociety.org/10.1109/TPAMI.2013.251>
Usage of this product signifies your acceptance of the Terms of Use.