This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Tree-Structured CRF Models for Interactive Image Labeling
Feb. 2013 (vol. 35 no. 2)
pp. 476-489
T. Mensink, LEAR Team, INRIA Rhone-Alpes, Montbonnot, France
J. Verbeek, LEAR Team, INRIA Rhone-Alpes, Montbonnot, France
G. Csurka, Xerox Res. Centre Eur. Grenoble, Meylan, France
We propose structured prediction models for image labeling that explicitly take into account dependencies among image labels. In our tree-structured models, image labels are nodes, and edges encode dependency relations. To allow for more complex dependencies, we combine labels in a single node and use mixtures of trees. Our models are more expressive than independent predictors, and lead to more accurate label predictions. The gain becomes more significant in an interactive scenario where a user provides the value of some of the image labels at test time. Such an interactive scenario offers an interesting tradeoff between label accuracy and manual labeling effort. The structured models are used to decide which labels should be set by the user, and transfer the user input to more accurate predictions on other image labels. We also apply our models to attribute-based image classification, where attribute predictions of a test image are mapped to class probabilities by means of a given attribute-class mapping. Experimental results on three publicly available benchmark datasets show that in all scenarios our structured models lead to more accurate predictions, and leverage user input much more effectively than state-of-the-art independent models.
Index Terms:
trees (mathematics),image classification,interactive systems,probability,benchmark datasets,tree-structured CRF models,interactive image labeling,structured prediction models,dependency relations,label predictions,interactive scenario,label accuracy,manual labeling effort,attribute-based image classification,class probabilities,attribute-class mapping,Predictive models,Vectors,Labeling,Image edge detection,Pattern recognition,Kernel,Training,statistical pattern recognition,Pattern recognition application computer vision,pattern recognition interactive systems,object recognition,content analysis and indexing
Citation:
T. Mensink, J. Verbeek, G. Csurka, "Tree-Structured CRF Models for Interactive Image Labeling," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 2, pp. 476-489, Feb. 2013, doi:10.1109/TPAMI.2012.100
Usage of this product signifies your acceptance of the Terms of Use.