Hashing with binary autoencoders

An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space. Finding the optimal hash function is difficult because it involves binary constraints, and most approaches approximate the optimization by relaxing the constraints and then binarizing the result. Here, we focus on the binary autoencoder model, which seeks to reconstruct an image from the binary code produced by the hash function. We show that the optimization can be simplified with the method of auxiliary coordinates. This reformulates the optimization as alternating two easier steps: one that learns the encoder and decoder separately, and one that optimizes the code for each image. Image retrieval experiments show the resulting hash function outperforms or is competitive with state-of-the-art methods for binary hashing.

[1]  J. Moreau.  Fonctions convexes duales et points proximaux dans un espace hilbertien , 1962 .

[2]  R. Rockafellar.  Monotone Operators and the Proximal Point Algorithm , 1976 .

[3]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[4]  Gene H. Golub,et al.  Matrix computations , 1983 .

[5]  D. Freedman,et al.  Asymptotics of Graphical Projection Pursuit , 1984 .

[6]  Ron Kohavi,et al.  The Wrapper Approach , 1998 .

[7]  Hiroshi Motoda,et al.  Feature Extraction, Construction and Selection: A Data Mining Perspective , 1998 .

[8]  Marc Teboulle,et al.  Global Optimality Conditions for Quadratic Optimization Problems with Binary Constraints , 2000, SIAM J. Optim..

[9]  Stephen J. Wright,et al.  Numerical Optimization (Springer Series in Operations Research and Financial Engineering) , 2000 .

[10]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[11]  Jianbo Shi,et al.  Multiclass spectral clustering , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

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

[13]  Alexandr Andoni,et al.  Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

[14]  Zhi-You Wu,et al.  Non-convex quadratic minimization problems with quadratic constraints: global optimality conditions , 2007, Math. Program..

[15]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

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

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

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

[19]  Trevor Darrell,et al.  Learning to Hash with Binary Reconstructive Embeddings , 2009, NIPS.

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

[21]  Geoffrey E. Hinton,et al.  Semantic hashing , 2009, Int. J. Approx. Reason..

[22]  Yong Xia,et al.  New optimality conditions for quadratic optimization problems with binary constraints , 2009, Optim. Lett..

[23]  Miguel Á. Carreira-Perpiñán,et al.  The Elastic Embedding Algorithm for Dimensionality Reduction , 2010, ICML.

[24]  Jun Wang,et al.  Self-taught hashing for fast similarity search , 2010, SIGIR.

[25]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

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

[27]  David J. Fleet,et al.  Minimal Loss Hashing for Compact Binary Codes , 2011, ICML.

[28]  Geoffrey E. Hinton,et al.  Using very deep autoencoders for content-based image retrieval , 2011, ESANN.

[29]  Patrick L. Combettes,et al.  Proximal Splitting Methods in Signal Processing , 2009, Fixed-Point Algorithms for Inverse Problems in Science and Engineering.

[30]  Wei Liu,et al.  Hashing with Graphs , 2011, ICML.

[31]  P. Whittle.  On principal components and least square methods of factor analysis , 2012 .

[32]  Shih-Fu Chang,et al.  Spherical hashing , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Kristen Grauman,et al.  Kernelized Locality-Sensitive Hashing , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  David Suter,et al.  A General Two-Step Approach to Learning-Based Hashing , 2013, 2013 IEEE International Conference on Computer Vision.

[35]  Ruslan Salakhutdinov,et al.  The Power of Asymmetry in Binary Hashing , 2013, NIPS.

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

[37]  David Suter,et al.  Fast Supervised Hashing with Decision Trees for High-Dimensional Data , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  Miguel Á. Carreira-Perpiñán,et al.  Distributed optimization of deeply nested systems , 2012, AISTATS.

[39]  Miguel Á. Carreira-Perpiñán.  An ADMM algorithm for solving a proximal bound-constrained quadratic program , 2014, ArXiv.

[40]  Miguel Á. Carreira-Perpiñán,et al.  Learning hashing with affinity-based loss functions using auxiliary coordinates , 2015, ArXiv.