Nonlinear Discrete Hashing

In this paper, we propose a nonlinear discrete hashing approach to learn compact binary codes for scalable image search. Instead of seeking a single linear projection in most existing hashing methods, we pursue a multilayer network with nonlinear transformations to capture the local structure of data samples. Unlike most existing hashing methods that adopt an error-prone relaxation to learn the transformations, we directly solve the discrete optimization problem to eliminate the quantization error accumulation. Specifically, to leverage the similarity relationships between data samples and exploit the semantic affinities of manual labels, the binary codes are learned with the objective to: 1) minimize the quantization error between the original data samples and the learned binary codes; 2) preserve the similarity relationships in the learned binary codes; 3) maximize the information content with independent bits; and 4) maximize the accuracy of the predicted labels based on the binary codes. With an alternating optimization, the nonlinear transformation and the discrete quantization are jointly optimized in the hashing learning framework. Experimental results on four datasets including CIFAR10, MNIST, SUN397, and ILSVRC2012 demonstrate that the proposed approach is superior to several state-of-the-art hashing methods.

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

[2]  Laurent Amsaleg,et al.  Supervised Multi-scale Locality Sensitive Hashing , 2015, ICMR.

[3]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

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

[5]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

[8]  Wei Liu,et al.  Compact Hyperplane Hashing with Bilinear Functions , 2012, ICML.

[9]  Wu-Jun Li,et al.  Double-Bit Quantization for Hashing , 2012, AAAI.

[10]  Seungjin Choi,et al.  Bilinear random projections for locality-sensitive binary codes , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  John Langford,et al.  Hash Kernels for Structured Data , 2009, J. Mach. Learn. Res..

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

[13]  Fumin Shen,et al.  Inductive Hashing on Manifolds , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Svetlana Lazebnik,et al.  Locality-sensitive binary codes from shift-invariant kernels , 2009, NIPS.

[15]  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 .

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

[17]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

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

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

[20]  L. Deng,et al.  The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] , 2012, IEEE Signal Processing Magazine.

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

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

[23]  Jiwen Lu,et al.  Deep hashing for compact binary codes learning , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[25]  Miguel Á. Carreira-Perpiñán,et al.  Hashing with binary autoencoders , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[27]  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).

[28]  Pushmeet Kohli,et al.  Computationally bounded retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Wei Liu,et al.  Discrete Graph Hashing , 2014, NIPS.

[30]  Shih-Fu Chang,et al.  Semi-Supervised Hashing for Large-Scale Search , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[32]  Jianxin Wu,et al.  Optimizing Ranking Measures for Compact Binary Code Learning , 2014, ECCV.

[33]  Shuicheng Yan,et al.  Weakly-supervised hashing in kernel space , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[34]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[35]  Moses Charikar,et al.  Similarity estimation techniques from rounding algorithms , 2002, STOC '02.

[36]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

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

[38]  Jian Sun,et al.  K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Sanjiv Kumar,et al.  Learning Binary Codes for High-Dimensional Data Using Bilinear Projections , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[41]  Zhuowen Tu,et al.  Deeply-Supervised Nets , 2014, AISTATS.

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

[43]  Qi Tian,et al.  Batch-Orthogonal Locality-Sensitive Hashing for Angular Similarity , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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