Dynamicity and Durability in Scalable Visual Instance Search

Visual instance search involves retrieving from a collection of images the ones that contain an instance of a visual query. Systems designed for visual instance search face the major challenge of scalability: a collection of a few million images used for instance search typically creates a few billion features that must be indexed. Furthermore, as real image collections grow rapidly, systems must also provide dynamicity, i.e., be able to handle on-line insertions while concurrently serving retrieval operations. Durability, which is the ability to recover correctly from software and hardware crashes, is the natural complement of dynamicity. Durability, however, has rarely been integrated within scalable and dynamic high-dimensional indexing solutions. This article addresses the issue of dynamicity and durability for scalable indexing of very large and rapidly growing collections of local features for instance retrieval. By extending the NV-tree, a scalable disk-based high-dimensional index, we show how to implement the ACID properties of transactions which ensure both dynamicity and durability. We present a detailed performance evaluation of the transactional NV-tree: (i) We show that the insertion throughput is excellent despite the overhead for enforcing the ACID properties; (ii) We also show that this transactional index is truly scalable using a standard image benchmark embedded in collections of up to 28.5 billion high-dimensional vectors; the largest single-server evaluations reported in the literature.

[1]  Laurent Amsaleg,et al.  NV-Tree: An Efficient Disk-Based Index for Approximate Search in Very Large High-Dimensional Collections , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ronald Fagin,et al.  Efficient similarity search and classification via rank aggregation , 2003, SIGMOD '03.

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

[4]  Laurent Amsaleg,et al.  Impact of Storage Technology on the Efficiency of Cluster-Based High-Dimensional Index Creation , 2012, DASFAA Workshops.

[5]  Zhe Wang,et al.  Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search , 2007, VLDB.

[6]  Ting Liu,et al.  Clustering Billions of Images with Large Scale Nearest Neighbor Search , 2007, 2007 IEEE Workshop on Applications of Computer Vision (WACV '07).

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

[8]  Laurent Amsaleg,et al.  Dynamic behavior of balanced NV-trees , 2008, CBMI.

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

[10]  Zhe L. Lin,et al.  Distance Encoded Product Quantization , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Eamonn J. Keogh Nearest Neighbor , 2010, Encyclopedia of Machine Learning.

[12]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

[13]  Eli Upfal,et al.  Finding near neighbors through cluster pruning , 2007, PODS '07.

[14]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Laurent Amsaleg,et al.  Locality sensitive hashing: A comparison of hash function types and querying mechanisms , 2010, Pattern Recognit. Lett..

[16]  Hamid Pirahesh,et al.  ARIES: a transaction recovery method supporting fine-granularity locking and partial rollbacks using write-ahead logging , 1998 .

[17]  Thomas Mensink,et al.  Improving the Fisher Kernel for Large-Scale Image Classification , 2010, ECCV.

[18]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[19]  Michael J. Carey,et al.  Performance of B+ tree concurrency control algorithms , 1993, The VLDB Journal.

[20]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[21]  Arnold W. M. Smeulders,et al.  UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking , 2016 .

[22]  Laurent Amsaleg,et al.  SSD Technology Enables Dynamic Maintenance of Persistent High-Dimensional Indexes , 2016, ICMR.

[23]  Anthony K. H. Tung,et al.  HashFile: An efficient index structure for multimedia data , 2011, 2011 IEEE 27th International Conference on Data Engineering.

[24]  Trevor Darrell,et al.  Locality-Sensitive Hashing Using Stable Distributions , 2006 .

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

[26]  Panos Kalnis,et al.  Quality and efficiency in high dimensional nearest neighbor search , 2009, SIGMOD Conference.

[27]  Jeffrey K. Uhlmann,et al.  Satisfying General Proximity/Similarity Queries with Metric Trees , 1991, Inf. Process. Lett..

[28]  David G. Lowe,et al.  Scalable Nearest Neighbor Algorithms for High Dimensional Data , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Changhu Wang,et al.  Indexing billions of images for sketch-based retrieval , 2013, ACM Multimedia.

[30]  Shih-Fu Chang,et al.  Semi-supervised hashing for scalable image retrieval , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[31]  Matthijs Douze,et al.  Searching in one billion vectors: Re-rank with source coding , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[32]  Xuelong Li,et al.  Complementary Projection Hashing , 2013, 2013 IEEE International Conference on Computer Vision.

[33]  Grigorios Tsoumakas,et al.  A Comprehensive Study Over VLAD and Product Quantization in Large-Scale Image Retrieval , 2014, IEEE Transactions on Multimedia.

[34]  Irving L. Traiger,et al.  The Recovery Manager of the System R Database Manager , 1981, CSUR.

[35]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[36]  Antonio Torralba,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition , 2022 .

[37]  Edward Y. Chang,et al.  Clustering for Approximate Similarity Search in High-Dimensional Spaces , 2002, IEEE Trans. Knowl. Data Eng..

[38]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[39]  Paul Over,et al.  Instance search retrospective with focus on TRECVID , 2017, International Journal of Multimedia Information Retrieval.

[40]  Victor S. Lempitsky,et al.  Efficient Indexing of Billion-Scale Datasets of Deep Descriptors , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Frédéric Jurie,et al.  Sampling Strategies for Bag-of-Features Image Classification , 2006, ECCV.

[42]  Nathan Marz,et al.  Big Data: Principles and best practices of scalable realtime data systems , 2015 .

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

[44]  Mayank Bawa,et al.  LSH forest: self-tuning indexes for similarity search , 2005, WWW '05.

[45]  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.

[46]  Laurent Amsaleg,et al.  Indexing and searching 100M images with map-reduce , 2013, ICMR.

[47]  Friedrich Fraundorfer,et al.  A Binning Scheme for Fast Hard Drive Based Image Search , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

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

[49]  Andreas Reuter,et al.  Transaction Processing: Concepts and Techniques , 1992 .

[50]  Laurent Amsaleg,et al.  NV-Tree: nearest neighbors at the billion scale , 2011, ICMR '11.

[51]  Fei Su,et al.  ALADDIN: A locality aligned deep model for instance search , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[52]  Andrew Zisserman,et al.  Three things everyone should know to improve object retrieval , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[53]  Hervé Jégou,et al.  A Comparison of Dense Region Detectors for Image Search and Fine-Grained Classification , 2014, IEEE Transactions on Image Processing.

[54]  Prateek Jain,et al.  Fast image search for learned metrics , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[55]  Moira C. Norrie,et al.  The PH-tree: a space-efficient storage structure and multi-dimensional index , 2014, SIGMOD Conference.

[56]  Cordelia Schmid,et al.  Evaluation of GIST descriptors for web-scale image search , 2009, CIVR '09.

[57]  Andrew W. Moore,et al.  An Investigation of Practical Approximate Nearest Neighbor Algorithms , 2004, NIPS.

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

[59]  Victor Lempitsky,et al.  The inverted multi-index , 2012, CVPR.

[60]  Jonathan Goldstein,et al.  When Is ''Nearest Neighbor'' Meaningful? , 1999, ICDT.

[61]  Olivier Buisson,et al.  A posteriori multi-probe locality sensitive hashing , 2008, ACM Multimedia.

[62]  Jian Sun,et al.  Optimized Product Quantization , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[63]  Shin'ichi Satoh,et al.  Faster R-CNN Features for Instance Search , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[64]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Computing k-Nearest Neighbors , 1975, IEEE Transactions on Computers.

[65]  Junsong Yuan,et al.  Efficient Object Instance Search Using Fuzzy Objects Matching , 2017, AAAI.

[66]  Panos Kalnis,et al.  Efficient and accurate nearest neighbor and closest pair search in high-dimensional space , 2010, TODS.