Deep Cauchy Hashing for Hamming Space Retrieval

Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding. With compact hash codes, Hamming space retrieval enables the most efficient constant-time search that returns data points within a given Hamming radius to each query, by hash table lookups instead of linear scan. However, subject to the weak capability of concentrating relevant images to be within a small Hamming ball due to mis-specified loss functions, existing deep hashing methods may underperform for Hamming space retrieval. This work presents Deep Cauchy Hashing (DCH), a novel deep hashing model that generates compact and concentrated binary hash codes to enable efficient and effective Hamming space retrieval. The main idea is to design a pairwise cross-entropy loss based on Cauchy distribution, which penalizes significantly on similar image pairs with Hamming distance larger than the given Hamming radius threshold. Comprehensive experiments demonstrate that DCH can generate highly concentrated hash codes and yield state-of-the-art Hamming space retrieval performance on three datasets, NUS-WIDE, CIFAR-10, and MS-COCO.

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

[2]  Jianmin Wang,et al.  Deep Quantization Network for Efficient Image Retrieval , 2016, AAAI.

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

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

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

[6]  Shiguang Shan,et al.  Deep Supervised Hashing for Fast Image Retrieval , 2016, International Journal of Computer Vision.

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

[8]  Shih-Fu Chang,et al.  Hash Bit Selection: A Unified Solution for Selection Problems in Hashing , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Philip S. Yu,et al.  Deep Visual-Semantic Hashing for Cross-Modal Retrieval , 2016, KDD.

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

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

[12]  Jianmin Wang,et al.  Deep Visual-Semantic Quantization for Efficient Image Retrieval , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[14]  Shih-Fu Chang,et al.  Circulant Binary Embedding , 2014, ICML.

[15]  Minyi Guo,et al.  Supervised hashing with latent factor models , 2014, SIGIR.

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

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

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

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

[20]  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).

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

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

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

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

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

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

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

[28]  Lucas C. Parra,et al.  Maximum Likelihood in Cost-Sensitive Learning: Model Specification, Approximations, and Upper Bounds , 2010, J. Mach. Learn. Res..

[29]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[30]  David J. Fleet,et al.  Fast search in Hamming space with multi-index hashing , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

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

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

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

[36]  Xianglong Liu,et al.  Collaborative Hashing , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.