Hierarchical deep hashing for image retrieval

Abstract

We present a new method to generate efficient multi-level hashing codes for image retrieval based on the deep siamese convolutional neural network (DSCNN). Conventional deep hashing methods trade off the capability of capturing highly complex and nonlinear semantic information of images against very compact hash codes, usually leading to high retrieval efficiency but with deteriorated accuracy. We alleviate the restrictive compactness requirement of hash codes by extending them to a two-level hierarchical coding scheme, in which the first level aims to capture the high-level semantic information extracted by the deep network using a rich encoding strategy, while the subsequent level squeezes them to more global and compact codes. At running time, we adopt an attention-based mechanism to select some of its most essential bits specific to each query image for retrieval instead of using the full hash codes of the first level. The attention-based mechanism is based on the guides of hash codes generated by the second level, taking advantage of both local and global properties of deep features. Experimental results on various popular datasets demonstrate the advantages of the proposed method compared to several state-of-the-art methods.

Keywords

image retrieval / deep hashing / hierarchical deep hashing

References

[1] Smeulders A W M, Worring M, Santini S, Gupta A, Jain R. Contentbased image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(12): 1349–1380

[2] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012, 25(2): 2012

[3] Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, 580–587

[4] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 1337–1342

[5] Zheng L, Yang Y, Tian Q. SIFT Meets CNN: a decade survey of instance retrieval. 2016, arXiv preprint arXiv:1608.01807

[6] Babenko A, Slesarev A, Chigorin A, Lempitsky V. Neural codes for image retrieval. In: Proceedings of European Conference on Computer Vision. 2014, 584–599

[7] Razavian A S, Azizpour H, Sullivan J, Carlsson S. CNN features offthe- shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2014, 512–519

[8] Babenko A, Lempitsky V. Aggregating deep convolutional features for image retrieval. In: Proceedings of the IEEE Conference on Computer Vision. 2015, 1269–1277

[9] Tolias G, Sicre R, Jégou H. Particular object retrieval with integral max-pooling of CNN activations. Computer Science, 2015

[10] Ng Y H, Yang F, Davis L S. Exploiting local features from deep networks for image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 53–61

[11] Zheng L, Zhao Y L, Wang S J, Wang J D, Tian Q. Good practice in CNN feature transfer. 2016, arXiv preprint arXiv:1604, 00133

[12] Zheng L, Wang S J, Wang J D, Tian Q. Accurate image search with multi-scale contextual evidences. International Journal of Computer Vision, 2016(1): 1–13

[13] Zhou B L, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 2921–2929

[14] Andoni A, Indyk P. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In: Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science. 2006, 459–468

[15] Liong V E, Lu J W, Wang G, Moulin P, Zhou J. Deep hashing for compact binary codes learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 2475–2483

[16] Zhao F, Huang Y Z, Wang L, Tan T N. Deep semantic ranking based hashing for multi-label image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 1556–1564

[17] Chang S F. Supervised hashing with kernels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2012, 2074–2081

[18] Gong Y C, Pawlowski M, Yang F, Brandy L, Bourdev L, Fergus R. Web scale photo hash clustering on a single machine. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 19–27

[19] Xia R K, Pan Y, Lai H J, Liu C, Yan S C. Supervised Hashing for Image Retrieval via Image Representation Learning. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence. 2014

[20] Li W J, Wang S, Kang W C. Feature learning based deep supervised hashing with pairwise labels. Computer Science, 2015

[21] Liu H M, Wang R P, Shan S G, Chen X L. Deep supervised hashing for fast image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 2064–2072

[22] Paulin M, Douze M, Harchaoui Z, Mairal J, Perronin F, Schmid C. Local convolutional features with unsupervised training for image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision. 2015, 91–99

[23] Kalantidis Y, Mellina C, Osindero S. Cross-dimensional weighting for aggregated deep convolutional features. In: Proceedings of European Conference on Computer Vision. 2016, 685–701

[24] Salvador A, Giroinieto X, Marques F, Satoh S I. Faster R-CNN features for instance search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2016, 9–16

[25] Lin K, Yang H F, Hsiao J H, Chen C S. Deep learning of binary hash codes for fast image retrieval. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2015, 27–35

[26] Lai H J, Pan Y, Liu Y, Yan S C. Simultaneous feature learning and hash coding with deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 3270–3278

[27] Zeiler M D, Fergus R. Visualizing and understanding convolutional networks. In: Proceedings of European Conference on Computer Vision. 2013, 818–833

[28] Mahendran A, Vedaldi A. Understanding deep image representations by inverting them. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 5188–5196

[29] Krizhevsky A. Learning multiple layers of features from tiny images. Technical Report. 2012

[30] Jegou H, Douze M, Schmid C. Hamming embedding and weak geometric consistency for large scale image search. In: Proceedings of European conference on computer vision. 2008, 304–317

[31] Philbin J, Chum O, Isard M, Sivic J, Zisserman A. Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of the IEEE International Conference on Computer Vision. 2007, 1–8

[32] Philbin J, Chum O, Isard M, Sivic J, Zisserman A. Lost in quantization: improving particular object retrieval in large scale image databases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2008, 1–8

[33] Nister D, Stewenius H. Scalable recognition with a vocabulary tree. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2006, 2161–2168

[34] Jia Y Q, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T. Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on Multimedia. 2014, 675–678

[35] Gong Y C, Lazebnik S. Iterative quantization: A procrustean approach to learning binary codes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2011, 817–824

[36] Weiss Y, Torralba A, Fergus R. Spectral hashing. In: Proceedings of the Neural Information Processing Systems Conference. 2008, 1753–1760

[37] Heo J P, Lee Y, He J, Chang S F, Yoon S E. Spherical hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2012, 2957–2964

[38] Jiang Q Y, Li W J. Scalable graph hashing with feature transformation. In: Proceedings of the International Conference on Artificial Intelligence. 2015, 331–337

[39] Lin G S, Shen C H, Shi Q F, van den Hengel A, Suter D. Fast supervised hashing with decision trees for high-dimensional data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, 1971–1978

[40] Shen F M, Shen C H, Liu W, Shen H T. Supervised discrete hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 37–45

[41] Zhang P C, Zhang W, Li W J, Guo M Y. Supervised hashing with latent factor models. In: Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2014, 173–182

[42] Kang W C, Li W J, Zhou Z H. Column sampling based discrete supervised hashing. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence. 2016

[43] Zhang R M, Lin L, Zhang R, Zuo W M, Zhang L. Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification. IEEE Transactions on Image Processing, 2015, 24(12): 4766–4779

[44] Arandjelovic R, Zisserman A. All about VLAD. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2013, 1578–1585

[45] Jégou H, Zisserman A. Triangulation embedding and democratic aggregation for image search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, 3310–3317

[46] Razavian A S, Sullivan J, Carlsson S, Maki A. Visual instance retrieval with deep convolutional networks. 2014, arXiv preprint arXiv:1412.6574

RIGHTS & PERMISSIONS

2017 Higher Education Press and Springer-Verlag Berlin Heidelberg