Bloom Filters and Compact Hash Codes for Efficient and Distributed Image Retrieval

This paper presents a novel method for efficient image retrieval, based on a simple and effective hashing of CNN features and the use of an indexing structure based on Bloom filters. These filters are used as gatekeepers for the database of image features, allowing to avoid to perform a query if the query features are not stored in the database and speeding up the query process, without affecting retrieval performance. Thanks to the limited memory requirements the system is suitable for mobile applications and distributed databases, associating each filter to a distributed portion of the database (database shard), addressing large scale archives and allowing query parallelization. Experimental validation has been performed on three standard image retrieval datasets, outperforming state-of-the-art hashing methods in terms of precision, while the proposed indexing method obtains a 2x speedup.

[1]  Antonio Torralba,et al.  Spectral Hashing , 2008, NIPS.

[2]  Bernd Girod,et al.  Large-Scale Query-by-Image Video Retrieval Using Bloom Filters , 2016, ArXiv.

[3]  Svetlana Lazebnik,et al.  Iterative quantization: A procrustean approach to learning binary codes , 2011, CVPR 2011.

[4]  Alberto Del Bimbo,et al.  Fisher Encoded Convolutional Bag-of-Windows for Efficient Image Retrieval and Social Image Tagging , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[5]  Cordelia Schmid,et al.  Product Quantization for Nearest Neighbor Search , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Burton H. Bloom,et al.  Space/time trade-offs in hash coding with allowable errors , 1970, CACM.

[7]  David Stutz,et al.  Neural Codes for Image Retrieval , 2015 .

[8]  Larry S. Davis,et al.  Exploiting local features from deep networks for image retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[9]  Michael Isard,et al.  Object retrieval with large vocabularies and fast spatial matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Michael Isard,et al.  Lost in quantization: Improving particular object retrieval in large scale image databases , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  David J. Fleet,et al.  Cartesian K-Means , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Victor S. Lempitsky,et al.  The Inverted Multi-Index , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Alberto Del Bimbo,et al.  Compact hash codes and data structures for efficient mobile visual search , 2015, 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).

[14]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Jian Sun,et al.  Optimized Product Quantization for Approximate Nearest Neighbor Search , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Svetlana Lazebnik,et al.  Locality-sensitive binary codes from shift-invariant kernels , 2009, NIPS.

[17]  Michael Mitzenmacher,et al.  Less hashing, same performance: Building a better Bloom filter , 2006, Random Struct. Algorithms.

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

[19]  Jingkuan Song,et al.  Scalable Multimedia Retrieval by Deep Learning Hashing with Relative Similarity Learning , 2015, ACM Multimedia.

[20]  Koichi Kise,et al.  Compressed representation of feature vectors using a Bloomier filter and its application to specific object recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[21]  Nicole Immorlica,et al.  Locality-sensitive hashing scheme based on p-stable distributions , 2004, SCG '04.

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

[23]  Jian Sun,et al.  K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Sanjiv Kumar,et al.  Learning Binary Codes for High-Dimensional Data Using Bilinear Projections , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Jie Lin,et al.  Tiny Descriptors for Image Retrieval with Unsupervised Triplet Hashing , 2015, 2016 Data Compression Conference (DCC).

[26]  Oscar M. Danielsson.  Category-Sensitive Hashing and Bloom Filter Based Descriptors for Online Keypoint Recognition , 2015, SCIA.

[27]  Jen-Hao Hsiao,et al.  Deep learning of binary hash codes for fast image retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[28]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[29]  C. V. Jawahar,et al.  Towards Exhaustive Pairwise Matching in Large Image Collections , 2012, ECCV Workshops.

[30]  Michael Mitzenmacher,et al.  Distance-Sensitive Bloom Filters , 2006, ALENEX.

[31]  Jie Lin,et al.  Compact Global Descriptors for Visual Search , 2015, 2015 Data Compression Conference.

[32]  Thomas Mensink,et al.  Image Classification with the Fisher Vector: Theory and Practice , 2013, International Journal of Computer Vision.

[33]  Yannis Avrithis,et al.  Locally Optimized Product Quantization for Approximate Nearest Neighbor Search , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Dan Feng,et al.  Locality-Sensitive Bloom Filter for Approximate Membership Query , 2012, IEEE Transactions on Computers.