Online Variable Coding Length Product Quantization for Fast Nearest Neighbor Search in Mobile Retrieval

Quantization methods are crucial for efficient nearest neighbor search in many applications such as image, music, or product search. As mobile devices are becoming increasingly more popular, the quantization methods on mobile devices are more important, because a large portion of the search queries are becoming performed on mobile devices. One important characteristic of the communication on mobile devices is the inherent unreliability of their communication channels. In order to adapt the quality changes of the communication channels, we need to change the coding length of the quantization accordingly. The existing quantization methods use fixed-length codebooks, and it is expensive to retrain another codebook with different coding length. In this paper, we propose a novel variable length product quantization framework that consists of a set of fast universal scalar quantizers. The framework is capable of producing variable length quantization without retraining the codebook. Each data vector is transformed into a new space to reduce the correlation across dimensions. A proper number of bits is allocated to represent the scalar component in each dimension according to the given coding length. For each component, we estimate its probability density function (PDF) and design an efficient universal scalar quantizer based on the PDF and the allocated bits. To reduce distortion, we learn a Gaussian mixture model for the data. The experimental results show that, compared to state-of-the-art product quantization methods, our approach can construct the codebooks online for variable coding lengths and achieve the comparable performance.

[1]  Kristen Grauman,et al.  Kernelized locality-sensitive hashing for scalable image search , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2]  Pascal Fua,et al.  LDAHash: Improved Matching with Smaller Descriptors , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[4]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

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

[6]  Wen Gao,et al.  Location Discriminative Vocabulary Coding for Mobile Landmark Search , 2011, International Journal of Computer Vision.

[7]  Vivek K. Goyal,et al.  Optimal quantization of random measurements in compressed sensing , 2009, 2009 IEEE International Symposium on Information Theory.

[8]  Javaria Ikram,et al.  Locality constraint neighbour embedding via Reference Patch , 2015, 2015 IEEE International Conference on Multimedia and Expo (ICME).

[9]  Antonio Torralba,et al.  Small codes and large image databases for recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Michael I. Jordan,et al.  On Convergence Properties of the EM Algorithm for Gaussian Mixtures , 1996, Neural Computation.

[11]  David L. Neuhoff,et al.  Quantization , 2022, IEEE Trans. Inf. Theory.

[12]  Huijun Gao,et al.  Feature Combination and the kNN Framework in Object Classification , 2016, IEEE Transactions on Neural Networks and Learning Systems.

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

[14]  Nanning Zheng,et al.  Universal and low-complexity quantizer design for compressive sensing image coding , 2013, 2013 Visual Communications and Image Processing (VCIP).

[15]  Jonathan Brandt,et al.  Transform coding for fast approximate nearest neighbor search in high dimensions , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Chengjun Liu,et al.  A novel locally linear KNN model for visual recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Khurram Shafique,et al.  Optimized Transform Coding for Approximate KNN Search , 2014, BMVC.

[18]  Eli Shechtman,et al.  In defense of Nearest-Neighbor based image classification , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Stepán Obdrzálek,et al.  Sub-linear Indexing for Large Scale Object Recognition , 2005, BMVC.

[20]  Wei Liu,et al.  Supervised Discrete Hashing , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[22]  Wen Gao,et al.  Pruning tree-structured vector quantizer towards low bit rate mobile visual search , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[23]  Mohamed Hefeeda,et al.  Dynamic Control of Receiver Buffers in Mobile Video Streaming Systems , 2013, IEEE Transactions on Mobile Computing.

[24]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[25]  Victor Lempitsky,et al.  Additive Quantization for Extreme Vector Compression , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Youji Feng,et al.  Fast Localization in Large-Scale Environments Using Supervised Indexing of Binary Features. , 2016, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[27]  Xueming Qian,et al.  Scalable Mobile Image Retrieval by Exploring Contextual Saliency , 2015, IEEE Transactions on Image Processing.

[28]  Bernd Girod,et al.  A Hybrid Mobile Visual Search System With Compact Global Signatures , 2015, IEEE Transactions on Multimedia.

[29]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.

[30]  Bhaskar D. Rao,et al.  Low-Complexity Source Coding Using Gaussian Mixture Models, Lattice Vector Quantization, and Recursive Coding with Application to Speech Spectrum Quantization , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[31]  Vijay Arya,et al.  On Managing Quality of Experience of Multiple Video Streams in Wireless Networks , 2015, IEEE Trans. Mob. Comput..

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

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

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

[35]  Victor S. Lempitsky,et al.  Tree quantization for large-scale similarity search and classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Jinhui Tang,et al.  Supervised Quantization for Similarity Search , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Christina Fragouli,et al.  MicroCast: Cooperative Video Streaming Using Cellular and Local Connections , 2016, IEEE/ACM Transactions on Networking.

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

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

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

[41]  Jian Sun,et al.  Joint Inverted Indexing , 2013, 2013 IEEE International Conference on Computer Vision.

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

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

[44]  Ming Yang,et al.  Compressing Deep Convolutional Networks using Vector Quantization , 2014, ArXiv.

[45]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

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

[47]  Yannis Avrithis Quantize and Conquer: A Dimensionality-Recursive Solution to Clustering, Vector Quantization, and Image Retrieval , 2013, 2013 IEEE International Conference on Computer Vision.

[48]  Rongrong Ji,et al.  Supervised hashing with kernels , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[49]  Falk Scholer,et al.  User performance versus precision measures for simple search tasks , 2006, SIGIR.

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

[51]  Jinhui Tang,et al.  Sparse composite quantization , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Wen Gao,et al.  Learning multiple codebooks for low bit rate mobile visual search , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[53]  Bernd Girod,et al.  Mobile Visual Search: Architectures, Technologies, and the Emerging MPEG Standard , 2011, IEEE MultiMedia.