ABSTRACT
Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets. To enable more effective triplet training, we design a new triplet selection approach, Group Hard, that randomly selects hard triplets in each image group. To generate compact binary codes, we further apply a triplet quantization with weak orthogonality during triplet training. The quantization loss reduces the codebook redundancy and enhances the quantizability of deep representations through back-propagation. Extensive experiments demonstrate that DTQ can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO.
- Yue Cao, Mingsheng Long, Jianmin Wang, and Shichen Liu. 2017. Deep visual-semantic quantization for efficient image retrieval. In CVPR.Google Scholar
- Yue Cao, Mingsheng Long, Jianmin Wang, Han Zhu, and Qingfu Wen. 2016. Deep Quantization Network for Efficient Image Retrieval. AAAI. Google ScholarDigital Library
- Zhangjie Cao, Mingsheng Long, Jianmin Wang, and Philip S Yu. 2017. HashNet: Deep Learning to Hash by Continuation. ICCV (2017).Google Scholar
- Tat-Seng Chua, Jinhui Tang, Richang Hong, Haojie Li, Zhiping Luo, and Yan-Tao Zheng. 2009. NUS-WIDE: A Real-World Web Image Database from National University of Singapore. In ICMR. ACM.Google Scholar
- Thanh-Toan Do, Anh-Dzung Doan, and Ngai-Man Cheung. 2016. Learning to hash with binary deep neural network. In ECCV. Springer.Google Scholar
- J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell. 2014. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In ICML. Google ScholarDigital Library
- Chao Du and Jingdong Wang. 2014. Inner Product Similarity Search using Compositional Codes. CoRR Vol. abs/1406.4966 (2014).Google Scholar
- Venice Erin Liong, Jiwen Lu, Gang Wang, Pierre Moulin, and Jie Zhou. 2015. Deep Hashing for Compact Binary Codes Learning. In CVPR. IEEE.Google Scholar
- D. J. Fleet, A. Punjani, and M. Norouzi. 2012. Fast search in Hamming space with multi-index hashing, In CVPR. CVPR. Google ScholarDigital Library
- Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2014. Optimized Product Quantization. TPAMI (2014). Google ScholarDigital Library
- Aristides Gionis, Piotr Indyk, Rajeev Motwani, et al. 1999. Similarity search in high dimensions via hashing. In VLDB, Vol. Vol. 99. ACM. Google ScholarDigital Library
- Yunchao Gong, Sudhakar Kumar, Henry Rowley, Svetlana Lazebnik, et al. 2013. Learning binary codes for high-dimensional data using bilinear projections. In CVPR. IEEE, 484--491. Google ScholarDigital Library
- Yunchao Gong and Svetlana Lazebnik. 2011. Iterative quantization: A procrustean approach to learning binary codes. In CVPR. 817--824. Google ScholarDigital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. CVPR (2016).Google Scholar
- Himalaya Jain, Joaquin Zepeda, Patrick Pérez, and Rémi Gribonval. 2017. SUBIC: A supervised, structured binary code for image search. In ICCV.Google Scholar
- H. Jegou, M. Douze, and C. Schmid. 2011. Product Quantization for Nearest Neighbor Search. TPAMI Vol. 33, 1 (Jan. 2011), 117--128. Google ScholarDigital Library
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS. Google ScholarDigital Library
- Brian Kulis and Trevor Darrell. 2009. Learning to hash with binary reconstructive embeddings. In NIPS. 1042--1050. Google ScholarDigital Library
- Hanjiang Lai, Yan Pan, Ye Liu, and Shuicheng Yan. 2015. Simultaneous Feature Learning and Hash Coding with Deep Neural Networks. In CVPR. IEEE.Google Scholar
- Wu-Jun Li, Sheng Wang, and Wang-Cheng Kang. 2016. Feature learning based deep supervised hashing with pairwise labels. In IJCAI. Google ScholarDigital Library
- Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In ECCV. Springer, 740--755.Google Scholar
- Haomiao Liu, Ruiping Wang, Shiguang Shan, and Xilin Chen. 2016. Deep supervised hashing for fast image retrieval. In CVPR. 2064--2072.Google Scholar
- Wei Liu, Jun Wang, Rongrong Ji, Yu-Gang Jiang, and Shih-Fu Chang. 2012. Supervised hashing with kernels. In CVPR. IEEE.Google Scholar
- Wei Liu, Jun Wang, Sanjiv Kumar, and Shih-Fu Chang. 2011. Hashing with Graphs. In ICML. ACM. Google ScholarDigital Library
- Xianglong Liu, Junfeng He, Bo Lang, and Shih-Fu Chang. 2013. Hash bit selection: a unified solution for selection problems in hashing. In CVPR. IEEE. Google ScholarDigital Library
- Mingsheng Long, Yue Cao, Jianmin Wang, and Philip S. Yu. 2016. Composite Correlation Quantization for Efficient Multimodal Retrieval. In SIGIR. Google ScholarDigital Library
- Mohammad Norouzi and David M. Blei. 2011. Minimal loss hashing for compact binary codes. In ICML. ACM, 353--360. Google ScholarDigital Library
- Mohammad Norouzi, David M. Blei, and Ruslan R. Salakhutdinov. 2012. Hamming distance metric learning. In NIPS. 1061--1069. Google ScholarDigital Library
- Ruslan Salakhutdinov and Geoffrey E. Hinton. 2007. Learning a nonlinear embedding by preserving class neighbourhood structure. In AISTATS. 412--419.Google Scholar
- Fumin Shen, Chunhua Shen, Wei Liu, and Heng Tao Shen. 2015. Supervised Discrete Hashing. In CVPR. IEEE.Google Scholar
- L. J. P van der Maaten and G. E. Hinton. Nov 2008. Visualizing High-Dimensional Data Using t-SNE. JMLR Vol. 9: 2579--2605 (Nov 2008).Google Scholar
- Jun Wang, Sanjiv Kumar, and Shih-Fu Chang. 2012. Semi-supervised hashing for large-scale search. TPAMI Vol. 34, 12 (2012), 2393--2406. Google ScholarDigital Library
- Jingdong Wang, Ting Zhang, Jingkuan Song, Nicu Sebe, and Heng Tao Shen. 2018. A Survey on Learning to Hash. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, 4 (Feb. 2018), 769--790.Google ScholarCross Ref
- Xiaojuan Wang, Ting Zhang, Guo-Jun Qi, Jinhui Tang, and Jingdong Wang. 2016. Supervised quantization for similarity search. In CVPR.Google Scholar
- Yair Weiss, Antonio Torralba, and Rob Fergus. 2009. Spectral Hashing. In NIPS.Google Scholar
- Rongkai Xia, Yan Pan, Hanjiang Lai, Cong Liu, and Shuicheng Yan. 2014. Supervised hashing for image retrieval via image representation learning. In AAAI. Google ScholarDigital Library
- Felix X. Yu, Sanjiv Kumar, Yunchao Gong, and Shih-Fu Chang. 2014. Circulant binary embedding. In ICML. ACM, 353--360. Google ScholarDigital Library
- Peichao Zhang, Wei Zhang, Wu-Jun Li, and Minyi Guo. 2014. Supervised hashing with latent factor models. In SIGIR. ACM, 173--182. Google ScholarDigital Library
- Ting Zhang, Chao Du, and Jingdong Wang. 2014. Composite Quantization for Approximate Nearest Neighbor Search. In ICML. ACM. Google ScholarDigital Library
- Liming Zhao, Xi Li, Jingdong Wang, and Yueting Zhuang. 2017. Deeply-learned part-aligned representations for person re-identification. In ICCV.Google Scholar
- Han Zhu, Mingsheng Long, Jianmin Wang, and Yue Cao. 2016. Deep Hashing Network for Efficient Similarity Retrieval. AAAI. Google ScholarDigital Library
Index Terms
- Deep Triplet Quantization
Recommendations
Deep Asymmetric Pairwise Hashing
MM '17: Proceedings of the 25th ACM international conference on MultimediaRecently, deep neural networks based hashing methods have greatly improved the multimedia retrieval performance by simultaneously learning feature representations and binary hash functions. Inspired by the latest advance in the asymmetric hashing scheme,...
Deep Priority Hashing
MM '18: Proceedings of the 26th ACM international conference on MultimediaDeep hashing enables image retrieval by end-to-end learning of deep representations and hash codes from training data with pairwise similarity information. Subject to the distribution skewness underlying the similarity information, most existing deep ...
Deep triplet residual quantization
Highlights- Offline training achieves promising results compared with online training.
- ...
AbstractQuantization techniques have been widely used in the approximate near neighbor similarity search, data compression, etc. Recently, metric learning based deep hashing methods take advantage of quantization techniques to accelerate the ...
Comments