Lu Chao
ABSTRACT
The increasing growth of image data has made the implementation of image retrieval in big data environment a hot research topic. Traditional hashing technique uses hand-designed features for learning, which can't obtain high-level semantic features. Deep hashing has become a powerful tool for solving multimedia data retrieval in recent years with the powerful feature learning capability and the inherent advantage of small hash code storage/fast retrieval. Most of these algorithms rely on manual tagging, which is very expensive. In this paper, we propose the Joint MLP and Pseudo-label unsupervised hash (JMPH). In this approach, object features in the image are extracted with the target detection method as pseudo-labels to train the deep hash. In particular, we additionally devise the MLP network to conduct the encoding process. Experimental results on two datasets demonstrate that our unsupervised hashing method outperforms the state-of-art unsupervised hashing methods.
- X. Luo, H. Wang, D. Wu, 2020. A survey on deep hashing methods. ACM Transactions on Knowledge Discovery from Data.Google Scholar
- A. Andoni, and P. Indyk. 2006. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. 2006 47th annual IEEE symposium on foundations of computer science (FOCS'06). IEEE, 459-468.Google Scholar
- B. Kulis, T. Darrell. 2009. Learning to hash with binary reconstructive embeddings. Advances in neural information processing systems, 22.Google Scholar
- H. Liu, R. Wang, S. Shan, 2016. Deep supervised hashing for fast image retrieval. Proceedings of the IEEE conference on computer vision and pattern recognition. 2064-2072.Google ScholarCross Ref
- R. Xia, Y. Pan, H. Lai, 2014. Supervised hashing for image retrieval via image representation learning. Twenty-eighth AAAI conference on artificial intelligence.Google ScholarDigital Library
- Z. Cao, M. Long, J. Wang, 2017. Hashnet: Deep learning to hash by continuation. Proceedings of the IEEE international conference on computer vision. 5608-5617.Google ScholarCross Ref
- W. Li, S. Wang, and W. Kang. 2015. Feature learning based deep supervised hashing with pairwise labels. arXiv preprint arXiv:1511.03855.Google Scholar
- K. Lin, J. Lu, C. S. Chen, 2016. Learning compact binary descriptors with unsupervised deep neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 1183-1192.Google ScholarCross Ref
- F. Shen, Y. Xu, L. Liu, 2018. Unsupervised deep hashing with similarity-adaptive and discrete optimization. IEEE transactions on pattern analysis and machine intelligence. 40(12): 3034-3044.Google ScholarDigital Library
- E. Yang, C. Deng, T. Liu, 2018. Semantic structure-based unsupervised deep hashing. Proceedings of the 27th international joint conference on artificial intelligence. 1064-1070.Google ScholarCross Ref
- Y. Liu, M. Cheng, F. Wang, 2020. Deep Hashing image retrieval methods. Journal of Image and Graphics, 25(07): 1296-1317.Google Scholar
- K. Dizaji, F. Zheng, N. Sadoughi, 2018. Unsupervised deep generative adversarial hashing network. Proceedings of the IEEE conference on computer vision and pattern recognition. 3664-3673.Google ScholarCross Ref
- Q. Hu, J. Wu, J. Cheng, 2017. Pseudo label based unsupervised deep discriminative hashing for image retrieval. Proceedings of the 25th ACM international conference on Multimedia. 1584-1590.Google ScholarDigital Library
- J. In, H. Liu. 2020. Deep Unsupervised Hashing with Pseudo Pairwise Labels. Pattern Recognition and Artificial Intelligence, 33(3), 258−267.Google Scholar
- S. Ren, K. He, R. Girshick, 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28.Google Scholar
- J. Song. 2021. Ufo-vit: High performance linear vision transformer without softmax. arXiv preprint arXiv:2109.14382.Google Scholar
- M. Everingham, S. Eslami, L. Van Gool, 2015. The pascal visual object classes challenge: A retrospective. International journal of computer vision. 111(1): 98-136.Google Scholar
- T. Lin, M. Maire, S. Belongie, 2014. Microsoft coco: Common objects in context. European conference on computer vision. 740-755.Google ScholarCross Ref
- Y. Weiss, A. Torralba, R. Fergus. 2008. Spectral hashing. Advances in neural information processing systems, 21.Google Scholar
- Y. Gong, S. Lazebnik, A. Gordo, 2012. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE transactions on pattern analysis and machine intelligence. 35(12): 2916-2929.Google Scholar
- K. Simonyan, A. Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.Google Scholar
Index Terms
- Joint MLP and Pseudo-label Unsupervised Hash for Image Retrieval
Recommendations
Pseudo Label based Unsupervised Deep Discriminative Hashing for Image Retrieval
MM '17: Proceedings of the 25th ACM international conference on MultimediaHashing methods play an important role in large scale image retrieval. Traditional hashing methods use hand-crafted features to learn hash functions, which can not capture the high level semantic information. Deep hashing algorithms use deep neural ...
Research on Pseudo-label Technology for Multi-label News Classification
Document Analysis and Recognition – ICDAR 2021AbstractMulti-label news classification exerts a significant importance with the growing size of news containing multiple semantics. However, most of the existing multi-label classification methods rely on large-scale labeled corpus while publicly ...
Semi-supervised Learning with Nearest-Neighbor Label and Consistency Regularization
Machine Learning for Cyber SecurityAbstractSemi-supervised learning, a system dedicated to making networks less dependent on labeled data, has become a popular paradigm due to its strong performance. A common approach is to use pseudo-labels with unlabeled data for training, however, ...
Comments