Indexation multimédia par dictionnaires visuels en environnement décentralisé. Une approche par protocoles Gossip

RÉSUMÉ. Pour permettre la recherche par le contenu de documents multimédias repartis sur de larges réseaux, nous proposons un système d’indexation basé sur l’apprentissage décentralisé et asynchrone de dictionnaires visuels. Nous proposons un algorithme décentralisé pour le calcul des dictionnaires basé sur un protocole d’agrégation Gossip, qui produit un dictionnaire local performant en chaque nœud du réseau. Nous fournissons une loi empirique pour déterminer les paramètres optimaux du système selon la taille du réseau ciblé, qui permettent d’obtenir des dictionnaires égaux entre nœuds pour un coût de communication faible. Une étude expérimentale met en évidence les capacités de passage à l’échelle et la qualité de recherche du système.

[1]  Cordelia Schmid,et al.  Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search , 2008, ECCV.

[2]  Giuseppe Patanè,et al.  The enhanced LBG algorithm , 2001, Neural Networks.

[3]  Matthieu Cord,et al.  An application of swarm intelligence to distributed image retrieval , 2012, Inf. Sci..

[4]  Raphaël Marée,et al.  Incremental indexing and distributed image search using shared randomized vocabularies , 2010, MIR '10.

[5]  Ujjwal Maulik,et al.  Clustering distributed data streams in peer-to-peer environments , 2006, Inf. Sci..

[6]  Wolfgang Müller,et al.  Classifying Documents by Distributed P2P Clustering , 2003, GI Jahrestagung.

[7]  Hillol Kargupta,et al.  K-Means Clustering Over a Large, Dynamic Network , 2006, SDM.

[8]  Doug Terry,et al.  Epidemic algorithms for replicated database maintenance , 1988, OPSR.

[9]  Nir Ailon,et al.  Streaming k-means approximation , 2009, NIPS.

[10]  Yihong Gong,et al.  Linear spatial pyramid matching using sparse coding for image classification , 2009, CVPR.

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

[12]  Cordelia Schmid,et al.  Aggregating Local Image Descriptors into Compact Codes , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Giancarlo Fortino,et al.  Epidemic K-Means Clustering , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[14]  Stephen P. Boyd,et al.  Randomized gossip algorithms , 2006, IEEE Transactions on Information Theory.

[15]  Devavrat Shah,et al.  Gossip Algorithms , 2009, Found. Trends Netw..

[16]  Marc Gelgon,et al.  Gossip-Based Computation of a Gaussian Mixture Model for Distributed Multimedia Indexing , 2008, IEEE Transactions on Multimedia.

[17]  Walid Hachem,et al.  Analysis of Sum-Weight-Like Algorithms for Averaging in Wireless Sensor Networks , 2012, IEEE Transactions on Signal Processing.

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

[19]  Fabrice Rossi,et al.  A Discussion on Parallelization Schemes for Stochastic Vector Quantization Algorithms , 2012, ESANN.

[20]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[21]  Adam Meyerson,et al.  Fast and Accurate k-means For Large Datasets , 2011, NIPS.

[22]  Tzu-Chuen Lu,et al.  A Survey of VQ Codebook Generation , 2010, J. Inf. Hiding Multim. Signal Process..

[23]  Giancarlo Fortino,et al.  Fault tolerant decentralised K-Means clustering for asynchronous large-scale networks , 2013, J. Parallel Distributed Comput..

[24]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[25]  John N. Tsitsiklis,et al.  Weighted Gossip: Distributed Averaging using non-doubly stochastic matrices , 2010, 2010 IEEE International Symposium on Information Theory.

[26]  Nikos A. Vlassis,et al.  Newscast EM , 2004, NIPS.

[27]  Cor J. Veenman,et al.  Visual Word Ambiguity , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Yihong Gong,et al.  Locality-constrained Linear Coding for image classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[29]  David Picard,et al.  Improving image similarity with vectors of locally aggregated tensors , 2011, 2011 18th IEEE International Conference on Image Processing.

[30]  Andreas Henrich,et al.  Efficient content-based P2P image retrieval using peer content descriptions , 2003, IS&T/SPIE Electronic Imaging.

[31]  Cordelia Schmid,et al.  Aggregating local descriptors into a compact image representation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[32]  M. V. Steen,et al.  Newscast Computing , 2003 .

[33]  Florent Perronnin,et al.  Fisher Kernels on Visual Vocabularies for Image Categorization , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[35]  Hans-Peter Kriegel,et al.  DBDC: Density Based Distributed Clustering , 2004, EDBT.

[36]  Hillol Kargupta,et al.  Approximate Distributed K-Means Clustering over a Peer-to-Peer Network , 2009, IEEE Transactions on Knowledge and Data Engineering.

[37]  Johannes Gehrke,et al.  Gossip-based computation of aggregate information , 2003, 44th Annual IEEE Symposium on Foundations of Computer Science, 2003. Proceedings..

[38]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[39]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .