Improved Search in Hamming Space Using Deep Multi-Index Hashing

Similarity-preserving hashing is a widely used method for nearest neighbor search in large-scale image retrieval tasks. Considerable research has been conducted on deep-network-based hashing approaches to improve the performance. However, the binary codes generated from deep networks may be not uniformly distributed over the Hamming space, which will greatly increase the retrieval time. To this end, we propose a deep-network-based multi-index hashing (MIH) for retrieval efficiency. We first introduce the MIH mechanism into the proposed deep architecture, which divides the binary codes into multiple substrings. Each substring corresponds to one hash table. Then, we add the two balanced constraints to obtain more uniformly distributed binary codes: 1) balanced substrings, where the Hamming distances of each substring are equal for any two binary codes and 2) balanced hash buckets, where the sizes of each bucket are equal. Extensive evaluations on several benchmark image retrieval data sets show that the learned balanced binary codes bring dramatic speedups and achieve comparable performance over the existing baselines.

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Jen-Hao Hsiao,et al.  Deep learning of binary hash codes for fast image retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[4]  Wu-Jun Li,et al.  Deep Cross-Modal Hashing , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

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

[8]  Geoffrey E. Hinton,et al.  Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure , 2007, AISTATS.

[9]  Matthijs Douze,et al.  How should we evaluate supervised hashing? , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Sheng Tang,et al.  Data driven multi-index hashing , 2013, 2013 IEEE International Conference on Image Processing.

[11]  Ling Shao,et al.  Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[13]  Devraj Mandal,et al.  Generalized Semantic Preserving Hashing for N-Label Cross-Modal Retrieval , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[15]  Jiangtao Cui,et al.  Multi-index hashing with repeat-bits in hamming space , 2015, 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[16]  Nicu Sebe,et al.  A Distance-Computation-Free Search Scheme for Binary Code Databases , 2016, IEEE Transactions on Multimedia.

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

[18]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[19]  Rossano Venturini,et al.  Fast and Compact Hamming Distance Index , 2016, IIR.

[20]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[21]  F. Frances Yao,et al.  Multi-index hashing for information retrieval , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[22]  Ian D. Reid,et al.  Fast Training of Triplet-Based Deep Binary Embedding Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  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).

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

[25]  Li Guo,et al.  Data-oriented multi-index hashing , 2015, 2015 IEEE International Conference on Multimedia and Expo (ICME).

[26]  David J. Fleet,et al.  Fast Exact Search in Hamming Space With Multi-Index Hashing , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[28]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

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

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

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

[32]  Venkatesh Saligrama,et al.  Efficient Training of Very Deep Neural Networks for Supervised Hashing , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[34]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

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

[36]  Chu-Song Chen,et al.  Supervised Learning of Semantics-Preserving Hashing via Deep Neural Networks for Large-Scale Image Search , 2015, ArXiv.

[37]  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.

[38]  Miroslaw Bober,et al.  Improved Hamming Distance Search Using Variable Length Hashing , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[40]  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).