Learning Class-to-Image Distance via Large Margin and L1-Norm Regularization

Image-to-Class (I2C) distance has demonstrated its effectiveness for object recognition in several single-label datasets. However, for the multi-label problem, where an image may contain several regions belonging to different classes, this distance may not work well since it cannot discriminate local features from different regions in the test image and all local features have to be counted in the I2C distance calculation. In this paper, we propose to use Class-to-Image (C2I) distance and show that this distance performs better than I2C distance for multi-label image classification. However, since the number of local features in a class is huge compared to that in an image, the calculation of C2I distance is much more expensive than I2C distance. Moreover, the label information of training images can be used to help select relevant local features for each class and further improve the recognition performance. Therefore, to make C2I distance faster and perform better, we propose an optimization algorithm using L1-norm regularization and large margin constraint to learn the C2I distance, which will not only reduce the number of local features in the class feature set, but also improve the performance of C2I distance due to the use of label information. Experiments on MSRC, Pascal VOC and MirFlickr datasets show that our method can significantly speed up the C2I distance calculation, while achieves better recognition performance than the original C2I distance and other related methods for multi-labeled datasets.

[1]  Jitendra Malik,et al.  Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[2]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[3]  Jitendra Malik,et al.  Image Retrieval and Classification Using Local Distance Functions , 2006, NIPS.

[4]  Trevor Darrell,et al.  The NBNN kernel , 2011, 2011 International Conference on Computer Vision.

[5]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[6]  Feiping Nie,et al.  Maximum Margin Multi-Instance Learning , 2011, NIPS.

[7]  Eli Shechtman,et al.  In defense of Nearest-Neighbor based image classification , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[10]  Véronique Prinet,et al.  Towards Optimal Naive Bayes Nearest Neighbor , 2010, ECCV.

[11]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

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

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

[14]  Feiping Nie,et al.  Learning Instance Specific Distance for Multi-Instance Classification , 2011, AAAI.

[15]  Christoph H. Lampert.  Maximum Margin Multi-Label Structured Prediction , 2011, NIPS.

[16]  Paul S. Bradley,et al.  Feature Selection via Concave Minimization and Support Vector Machines , 1998, ICML.

[17]  Cordelia Schmid,et al.  Image annotation with tagprop on the MIRFLICKR set , 2010, MIR '10.

[18]  Liang-Tien Chia,et al.  Improved learning of I2C distance and accelerating the neighborhood search for image classification , 2011, Pattern Recognit..

[19]  Florent Perronnin,et al.  Large-scale image retrieval with compressed Fisher vectors , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[20]  David G. Lowe,et al.  Local Naive Bayes Nearest Neighbor for image classification , 2011, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Bart Thomee,et al.  New trends and ideas in visual concept detection: the MIR flickr retrieval evaluation initiative , 2010, MIR '10.

[22]  Liang-Tien Chia,et al.  Image-to-Class Distance Metric Learning for Image Classification , 2010, ECCV.

[23]  Luc Van Gool,et al.  Iterative Nearest Neighbors for classification and dimensionality reduction , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Andrew Zisserman,et al.  An Exemplar Model for Learning Object Classes , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Chih-Jen Lin,et al.  A Comparison of Optimization Methods and Software for Large-scale L1-regularized Linear Classification , 2010, J. Mach. Learn. Res..