Image classification with saliency region and multi-task learning

In this paper, we propose a novel image classification method based on saliency region and multi-task learning (MTL). The proposed method has the advantages of both region-based and MTL-based methods. Specifically, we first detect the object region of an image with saliency detection technique, then extract its visual features, and then cluster them into groups, and finally employ MTL and SVM to build the classifier. Experimental results on two popular data sets (Corel and Caltech 101) have shown that our method has satisfactory classification performances and outperforms the traditional methods employing only region information or MTL.

[1]  Jing Wang,et al.  Scene image classification with biased spatial block and pLSA , 2012 .

[2]  Meng Wang,et al.  Semi-supervised kernel density estimation for video annotation , 2009, Comput. Vis. Image Underst..

[3]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[4]  David A. Forsyth,et al.  Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary , 2002, ECCV.

[5]  Vladimir Cherkassky,et al.  Connection between SVM+ and multi-task learning , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[6]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[7]  Jing Wang,et al.  Balance between object and background: Object-enhanced features for scene image classification , 2013, Neurocomputing.

[8]  Meng Wang,et al.  Beyond Distance Measurement: Constructing Neighborhood Similarity for Video Annotation , 2009, IEEE Transactions on Multimedia.

[9]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[10]  Bo Geng,et al.  Manifold Regularized Multi-task Learning for Semi-supervised Multi-label Image Classification , 2013 .

[11]  Robert Marti,et al.  Which is the best way to organize/classify images by content? , 2007, Image Vis. Comput..

[12]  Vladimir Cherkassky,et al.  Generalized SMO Algorithm for SVM-Based Multitask Learning , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Shi-Min Hu,et al.  Global contrast based salient region detection , 2011, CVPR 2011.

[14]  Meng Wang,et al.  Unified Video Annotation via Multigraph Learning , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  Tommy W. S. Chow,et al.  A new image classification technique using tree-structured regional features , 2007, Neurocomputing.

[16]  Donald Gustafson,et al.  Fuzzy clustering with a fuzzy covariance matrix , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.