RankCNN: When learning to rank encounters the pseudo preference feedback

Learning to rank has received great attentions in the field of text retrieval for several years. However, a few researchers introduce the topic into visual reranking due to the special nature of image presentation. In this paper, a novel unsupervised visual reranking is proposed, termed rank via the convolutional neural networks (RankCNN). This approach integrates deep learning with pseudo preference feedback. The optimal set of pseudo preference pairs is first detected from initial list by a modified graph-based method. Ranking is then reduced to pairwise classification in the architecture of CNN. In addition, Accelerated Mini-Batch Stochastic Dual Coordinate Ascent (ASDCA) is introduced to the framework to accelerate the training. The experiments indicate the competitive performance on the LETOR 4.0, the Paris and the Francelandmark dataset.

[1]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Robert Shelton,et al.  Computational intelligence standards: motivation, current activities and progress , 1994 .

[3]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[4]  Noboru Murata,et al.  A Statistical Study on On-line Learning , 1999 .

[5]  Léon Bottou,et al.  The Tradeoffs of Large Scale Learning , 2007, NIPS.

[6]  Martin A. Riedmiller,et al.  Advanced supervised learning in multi-layer perceptrons — From backpropagation to adaptive learning algorithms , 1994 .

[7]  Yann LeCun,et al.  Large Scale Online Learning , 2003, NIPS.

[8]  Yoram Singer,et al.  An Efficient Boosting Algorithm for Combining Preferences by , 2013 .

[9]  Cordelia Schmid,et al.  Accurate Image Search Using the Contextual Dissimilarity Measure , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Tie-Yan Liu,et al.  Learning to rank: from pairwise approach to listwise approach , 2007, ICML '07.

[11]  Ming Yang,et al.  Query Specific Fusion for Image Retrieval , 2012, ECCV.

[12]  Thorsten Joachims,et al.  Making large-scale support vector machine learning practical , 1999 .

[13]  Yuan Dong,et al.  An efficient graph-based visual reranking , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[14]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[15]  Luc Van Gool,et al.  Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors , 2011, CVPR 2011.

[16]  Klaus Obermayer,et al.  Support vector learning for ordinal regression , 1999 .

[18]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[19]  Tong Zhang,et al.  Solving large scale linear prediction problems using stochastic gradient descent algorithms , 2004, ICML.

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

[21]  Shai Shalev-Shwartz,et al.  Stochastic dual coordinate ascent methods for regularized loss , 2012, J. Mach. Learn. Res..

[22]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[23]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[24]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[25]  Xing-Yuan Wang,et al.  An effective method for color image retrieval based on texture , 2012, Comput. Stand. Interfaces.

[26]  Shai Shalev-Shwartz,et al.  Accelerated Mini-Batch Stochastic Dual Coordinate Ascent , 2013, NIPS.

[27]  Tao Mei,et al.  Learning to video search rerank via pseudo preference feedback , 2008, 2008 IEEE International Conference on Multimedia and Expo.