ABSTRACT
Learning-based hashing methods are becoming the mainstream for approximate scalable multimedia retrieval. They consist of two main components: hash codes learning for training data and hash functions learning for new data points. Tremendous efforts have been devoted to designing novel methods for these two components, i.e., supervised and unsupervised methods for learning hash codes, and different models for inferring hashing functions. However, there is little work integrating supervised and unsupervised hash codes learning into a single framework. Moreover, the hash function learning component is usually based on hand-crafted visual features extracted from the training images. The performance of a content-based image retrieval system crucially depends on the feature representation and such hand-crafted visual features may degrade the accuracy of the hash functions. In this paper, we propose a semi-supervised deep learning hashing (DLH) method for fast multimedia retrieval. More specifically, in the first component, we utilize both visual and label information to learn an relative similarity graph that can more precisely reflect the relationship among training data, and then generate the hash codes based on the graph. In the second stage, we apply a deep convolutional neural network (CNN) to simultaneously learn a good multimedia representation and hash functions. Extensive experiments on three popular datasets demonstrate the superiority of our DLH over both supervised and unsupervised hashing methods.
- L. Gao, J. Song, F. Nie, Y. Yan, N. Sebe, and H. T. Shen. Optimal graph leaning with partial tags and multiple features. In CVPR, 2015.Google ScholarCross Ref
- Y. Gong, S. Lazebnik, A. Gordo, and F. Perronnin. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. TPAMI, 35(12):2916--2929, 2013. Google ScholarDigital Library
- K. He, F. Wen, and J. Sun. K-means hashing: An affinity-preserving quantization method for learning binary compact codes. In CVPR, 2013. Google ScholarDigital Library
- Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093, 2014.Google Scholar
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012.Google ScholarDigital Library
- H. Lai, Y. Pan, Y. Liu, and S. Yan. Simultaneous feature learning and hash coding with deep neural networks. In CVPR, 2015.Google ScholarCross Ref
- G. Lin, C. Shen, Q. Shi, A. van den Hengel, and D. Suter. Fast supervised hashing with decision trees for high-dimensional data. In CVPR, 2014. Google ScholarDigital Library
- W. Liu, J. Wang, R. Ji, Y. Jiang, and S. Chang. Supervised hashing with kernels. In CVPR, 2012.Google Scholar
- J. Song, Y. Yang, Z. Huang, H. T. Shen, and R. Hong. Multiple feature hashing for real-time large scale near-duplicate video retrieval. In ACM Multimedia, 2011. Google ScholarDigital Library
- J. Wan, D. Wang, S. C. H. Hoi, P. Wu, J. Zhu, Y. Zhang, and J. Li. Deep learning for content-based image retrieval: A comprehensive study. In ACM Multimedia, 2014. Google ScholarDigital Library
- J. Wang, H. T. Shen, J. Song, and J. Ji. Hashing for similarity search: A survey. CoRR, abs/1408.2927, 2014.Google Scholar
- Y. Weiss, A. Torralba, and R. Fergus. Spectral hashing. In NIPS, 2008.Google ScholarDigital Library
- R. Xia, Y. Pan, H. Lai, C. Liu, and S. Yan. Supervised hashing for image retrieval via image representation learning. In AAAI, 2014.Google ScholarDigital Library
- S. Zhang, M. Yang, T. Cour, K. Yu, and D. N. Metaxas. Query specific fusion for image retrieval. In ECCV, 2012. Google ScholarDigital Library
Index Terms
- Scalable Multimedia Retrieval by Deep Learning Hashing with Relative Similarity Learning
Recommendations
Supervised Hashing with Pseudo Labels for Scalable Multimedia Retrieval
MM '15: Proceedings of the 23rd ACM international conference on MultimediaThere is an increasing interest in using hash codes for efficient multimedia retrieval and data storage. The hash functions are learned in such a way that the hash codes can preserve essential properties of the original space or the label information. ...
Supervised deep hashing for scalable face image retrieval
We propose a novel Deep Hashing based on Classification and Quantization errors for face image retrieval.It jointly learns feature representations of images, hashing functions and classifiers.The quantization errors and the prediction errors jointly ...
Classification-enhancement deep hashing for large-scale video retrieval
AbstractWith the explosive growth of video data on the Internet, retrieving and detecting similar video contents effectively has become a challenging problem. Whereas hashing is a mature technique for dealing with this problem, especially in ...
Highlights- Triplet-wise loss is applied into video hashing for similarity preserving.
- Add ...
Comments