Leveraging Quadratic Spherical Mutual Information Hashing for Fast Image Retrieval

Several deep supervised hashing techniques have been proposed to allow for querying large image databases. However, it is often overlooked that the process of information retrieval can be modeled using information-theoretic metrics, leading to optimizing various proxies for the problem at hand instead. Contrary to this, we propose a deep supervised hashing algorithm that optimizes the learned codes using an information-theoretic measure, the Quadratic Mutual Information (QMI). The proposed method is adapted to the needs of large-scale hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI), that is inspired by QMI, but leads to significant better retrieval precision. Indeed, the effectiveness of the proposed method is demonstrated under several different scenarios, using different datasets and network architectures, outperforming existing deep supervised image hashing techniques.

[1]  Jie Qin,et al.  Embarrassingly Simple Binary Representation Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[2]  Jianmin Wang,et al.  HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[4]  Stan Sclaroff,et al.  Hashing with Mutual Information , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Anastasios Tefas,et al.  Learning bag-of-embedded-words representations for textual information retrieval , 2018, Pattern Recognit..

[6]  Dacheng Tao,et al.  Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[7]  Nicholas I. Fisher,et al.  Statistical Analysis of Circular Data , 1993 .

[8]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[9]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[10]  Hanjiang Lai,et al.  Simultaneous feature learning and hash coding with deep neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Philip S. Yu,et al.  HashNet: Deep Learning to Hash by Continuation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[12]  Tat-Seng Chua,et al.  NUS-WIDE: a real-world web image database from National University of Singapore , 2009, CIVR '09.

[13]  Wai Keung Wong,et al.  Deep Supervised Hashing With Anchor Graph , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  Jianmin Wang,et al.  Deep Hashing Network for Efficient Similarity Retrieval , 2016, AAAI.

[15]  Nicu Sebe,et al.  Content-based multimedia information retrieval: State of the art and challenges , 2006, TOMCCAP.

[16]  Kari Torkkola,et al.  Feature Extraction by Non-Parametric Mutual Information Maximization , 2003, J. Mach. Learn. Res..

[17]  Wu-Jun Li,et al.  Feature Learning Based Deep Supervised Hashing with Pairwise Labels , 2015, IJCAI.

[18]  Lei Zhang,et al.  Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification , 2015, IEEE Transactions on Image Processing.

[19]  Jean-Pierre Chevallet,et al.  A Comparison of Deep Learning Based Query Expansion with Pseudo-Relevance Feedback and Mutual Information , 2016, ECIR.

[20]  Mark Sanderson,et al.  Christopher D. Manning, Prabhakar Raghavan, Hinrich Schütze, Introduction to Information Retrieval, Cambridge University Press 2008. ISBN-13 978-0-521-86571-5, xxi + 482 pages , 2010, Natural Language Engineering.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Kun He,et al.  MIHash: Online Hashing with Mutual Information , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[23]  Nicu Sebe,et al.  A Survey on Learning to Hash , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Jiwen Lu,et al.  Relaxation-Free Deep Hashing via Policy Gradient , 2018, ECCV.

[25]  I. C. Mogotsi,et al.  Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze: Introduction to information retrieval , 2010, Information Retrieval.

[26]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Jose C. Principe,et al.  Information Theoretic Learning - Renyi's Entropy and Kernel Perspectives , 2010, Information Theoretic Learning.

[28]  Anastasios Tefas,et al.  Entropy Optimized Feature-Based Bag-of-Words Representation for Information Retrieval , 2016, IEEE Transactions on Knowledge and Data Engineering.

[29]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[30]  Xin Luo,et al.  Discrete Hashing With Multiple Supervision , 2019, IEEE Transactions on Image Processing.

[31]  Jun Guo,et al.  Improving Retrieval Performance by Global Analysis , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[32]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[33]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[34]  Shiguang Shan,et al.  Deep Supervised Hashing for Fast Image Retrieval , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[36]  Hanjiang Lai,et al.  Supervised Hashing for Image Retrieval via Image Representation Learning , 2014, AAAI.

[37]  Tieniu Tan,et al.  Deep semantic ranking based hashing for multi-label image retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).