Large-Scale Visual Search with Binary Distributed Graph at Alibaba

Graph-based approximate nearest neighbor search has attracted more and more attentions due to its online search advantages. Numbers of methods studying the enhancement of speed and recall have been put forward. However, few of them focus on the efficiency and scale of offline graph-construction. For a deployed visual search system with several billions of online images in total, building a billion-scale offline graph in hours is essential, which is almost unachievable by most existing methods. In this paper, we propose a novel algorithm called Binary Distributed Graph to solve this problem. Specifically, we combine binary codes with graph structure to speedup both offline and online procedures, and achieve comparable performance with the ones that use real-value features, by recalling and reranking more binary candidates. Furthermore, the graph-construction is optimized to completely distributed implementation, which significantly accelerates the offline process and gets rid of the limitation of single machine, such as memory and storage. Experimental comparisons on Alibaba Commodity Data Set (more than three billion images) show that the proposed method outperforms the state-of-the-art with respect to the online/offline trade-off.

[1]  Tom Drummond,et al.  FANNG: Fast Approximate Nearest Neighbour Graphs , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Takeaki Uno,et al.  Efficient Construction of Neighborhood Graphs by the Multiple Sorting Method , 2009, ArXiv.

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

[4]  Hongtao Lu,et al.  Locality Preserving Hashing , 2014, AAAI.

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

[6]  Vladimir Krylov,et al.  Approximate nearest neighbor algorithm based on navigable small world graphs , 2014, Inf. Syst..

[7]  Richard I. Hartley,et al.  Optimised KD-trees for fast image descriptor matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[9]  Jing Wang,et al.  Scalable k-NN graph construction for visual descriptors , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Beng Chin Ooi,et al.  Selective Hashing: Closing the Gap between Radius Search and k-NN Search , 2015, KDD.

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

[12]  Rong Jin,et al.  Visual Search at Alibaba , 2018, KDD.

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

[14]  Fei Yang,et al.  Web scale photo hash clustering on a single machine , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Lei Shi,et al.  Fast Algorithm for Approximate k-Nearest Neighbor Graph Construction , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[16]  Wan-Lei Zhao.  k-NN Graph Construction: a Generic Online Approach , 2018, ArXiv.

[17]  Jie Gui.  R 2 SDH : Robust Rotated Supervised Discrete Hashing , 2018 .

[18]  Wu-Jun Li,et al.  Isotropic Hashing , 2012, NIPS.

[19]  Matthijs Douze,et al.  Link and Code: Fast Indexing with Graphs and Compact Regression Codes , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Hans-Peter Kriegel,et al.  The R*-tree: an efficient and robust access method for points and rectangles , 1990, SIGMOD '90.

[21]  Shipeng Li,et al.  Query-driven iterated neighborhood graph search for large scale indexing , 2012, ACM Multimedia.

[22]  Matthijs Douze,et al.  Polysemous Codes , 2016, ECCV.

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

[24]  Chun Chen,et al.  Harmonious Hashing , 2013, IJCAI.

[25]  Kiyoharu Aizawa,et al.  PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization Using Hash Tables , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  Beng Chin Ooi,et al.  iDistance: An adaptive B+-tree based indexing method for nearest neighbor search , 2005, TODS.

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

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

[29]  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).

[30]  Hongtao Lu,et al.  Locality Preserving Discriminative Hashing , 2014, ACM Multimedia.

[31]  Yury A. Malkov,et al.  Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Victor S. Lempitsky,et al.  Product Split Trees , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Kai Li,et al.  Efficient k-nearest neighbor graph construction for generic similarity measures , 2011, WWW.

[34]  Philip S. Yu,et al.  Deep Visual-Semantic Hashing for Cross-Modal Retrieval , 2016, KDD.