Image Classification by Labeled Data in Similar Topics

One of the most difficulties in image classification is the short availability of labeled images. However, in many cases, we can find a large amount of auxiliary labeled images to help the target classification. The auxiliary images are in similar topics of the target images. For example,donkey may be used as auxiliary data of horse, since they are quite similar with each other. In this paper, we propose to use similar but different labeled images as auxiliary data to help train image classifiers. An SVM-based classification algorithm is proposed to tackle our problem. Our algorithm first maximizes the margin between the decision boundary and the training instances, and then minimizes the penalty corresponding to misclassification. We conduct extensive experiments to demonstrate the effectiveness of our algorithm. The experimental results show that our algorithm can greatly improve the image classification performance by making use of similar labeled image as auxiliary data, against several state-of-the-art image classification algorithms.

[1]  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.

[2]  Qiang Yang,et al.  Co-clustering based classification for out-of-domain documents , 2007, KDD '07.

[3]  Alexei A. Efros,et al.  Discovering object categories in image collections , 2005 .

[4]  Koby Crammer,et al.  Analysis of Representations for Domain Adaptation , 2006, NIPS.

[5]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[6]  Thorsten Joachims,et al.  Learning to classify text using support vector machines - methods, theory and algorithms , 2002, The Kluwer international series in engineering and computer science.

[7]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[8]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[9]  Trevor Darrell,et al.  The pyramid match kernel: discriminative classification with sets of image features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[10]  Qiang Yang,et al.  Boosting for transfer learning , 2007, ICML '07.

[11]  Thomas G. Dietterich,et al.  Improving SVM accuracy by training on auxiliary data sources , 2004, ICML.

[12]  Luc Van Gool,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[13]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Fei-Fei Li,et al.  Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[15]  Daniel Gatica-Perez,et al.  PLSA-based image auto-annotation: constraining the latent space , 2004, MULTIMEDIA '04.

[16]  John Blitzer,et al.  Domain Adaptation with Structural Correspondence Learning , 2006, EMNLP.

[17]  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).

[18]  Lawrence Carin,et al.  Logistic regression with an auxiliary data source , 2005, ICML.

[19]  Qiang Yang,et al.  Transferring Naive Bayes Classifiers for Text Classification , 2007, AAAI.

[20]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[21]  Li Fei-Fei,et al.  Spatially coherent latent topic model for concurrent object segmentation and classification , 2007 .

[22]  Cordelia Schmid,et al.  A maximum entropy framework for part-based texture and object recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[23]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[24]  Yong Yu,et al.  Bridged Refinement for Transfer Learning , 2007, PKDD.

[25]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[26]  David R. Rosseinsky,et al.  A test of magnetic field effects on an electron-transfer system: adiabatic or not? , 2009 .

[27]  Daniel Marcu,et al.  Domain Adaptation for Statistical Classifiers , 2006, J. Artif. Intell. Res..

[28]  Koby Crammer,et al.  Learning Bounds for Domain Adaptation , 2007, NIPS.

[29]  Thomas G. Dietterich,et al.  To transfer or not to transfer , 2005, NIPS 2005.

[30]  Jitendra Malik,et al.  Shape matching and object recognition using low distortion correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[31]  Hal Daumé,et al.  Frustratingly Easy Domain Adaptation , 2007, ACL.

[32]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .