Weida Cao
ABSTRACT
Deep hashing methods has gained growing popularity in approximate nearest neighbour search for large-scale image retrieval, but exhibit undesirable behaviors such as sensitivity to adversarial examples. In the paper, inspired by the success of mixup-based data augmentation in adversarial training, we for the first time apply this technique to deep hash codes-based image retrieval, and evaluate its performance on six kinds of typical deep hashing methods. Experiments show that the mixup augmentation indeed could provide stable performance gains, ranging from 0.2% to 1.3%.
- Cong Fu, Chao Xiang, Changxu Wang, and Deng Cai. 2017. Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143 (2017).Google Scholar
- Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2013. Optimized product quantization for approximate nearest neighbor search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2946–2953.Google ScholarDigital Library
- Moses S Charikar. 2002. Similarity estimation techniques from rounding algorithms. In Proceedings of the thiry-fourth annual ACM symposium on Theory of computing. 380–388.Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012), 1097–1105.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.Google ScholarCross Ref
- Alex Krizhevsky, Geoffrey Hinton, 2009. Learning multiple layers of features from tiny images. (2009)Google Scholar
- Tat-Seng Chua, Jinhui Tang, Richang Hong, Haojie Li, Zhiping Luo, and Yantao Zheng. 2009. Nus-wide: a real-world web image database from national university of singapore. In Proceedings of the ACM international conference on image and video retrieval. 1–9.Google ScholarDigital Library
- Haomiao Liu, Ruiping Wang, Shiguang Shan, and Xilin Chen. 2016. Deep supervised hashing for fast image retrieval. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2064–2072.Google ScholarCross Ref
- Wu-Jun Li, Sheng Wang, and Wang-Cheng Kang. 2015. Feature learning based deep supervised hashing with pairwise labels. arXiv preprint arXiv:1511.03855 (2015).Google ScholarDigital Library
- Qi Li, Z. Sun, Ran He, T Tan. 2017.Deep supervised discrete hashing. arXiv preprint arXiv:1705.10999 (2017).Google Scholar
- Zhangjie Cao, Mingsheng Long, Jianmin Wang, and Philip S Yu. 2017. Hashnet: Deep learning to hash by continuation. In Proceedings of the IEEE international conference on computer vision. 5608–5617.Google ScholarCross Ref
- S Su, C Zhang, K Han, Y Tian. 2018. Greedy hash: Towards fast optimization for accurate hash coding in cnn. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 806-815.Google Scholar
- Lixin Fan, Kam Woh Ng, Ce Ju, Tianyu Zhang, and Chee Seng Chan. [n.d.]. Deep polarized network for supervised learning of accurate binary hashing codes. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20. 825–831.Google Scholar
- Piotr Indyk, Rajeev Motwani, Prabhakar Raghavan, and Santosh Vempala. 1997. Locality-preserving hashing in multidimensional spaces. In Proceedings of the twenty-ninth annual ACM symposium on Theory of computing. 618–625.Google ScholarDigital Library
- Venice Erin Liong, Jiwen Lu, GangWang, Pierre Moulin, and Jie Zhou. 2015. Deep hashing for compact binary codes learning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2475–2483.Google ScholarCross Ref
- Rongkai Xia, Yan Pan, Hanjiang Lai, Cong Liu, and Shuicheng Yan. 2014. Supervised hashing for image retrieval via image representation learning. In Proceedings of the AAAI conference on artificial intelligence, Vol. 28.Google ScholarCross Ref
- Fatih Cakir, Kun He, Sarah Adel Bargal, and Stan Sclaroff. 2019. Hashing with mutual information. IEEE transactions on pattern analysis and machine intelligence 41, 10 (2019), 2424–2437.Google Scholar
- Yue Cao, Mingsheng Long, Bin Liu, and Jianmin Wang. 2018. Deep Cauchy hashing for hamming space retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1229–1237.Google ScholarCross Ref
- Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199.Google Scholar
- Kun He, Fatih Cakir, Sarah Adel Bargal, and Stan Sclaroff. 2018. Hashing as tie-aware learning to rank. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4023–4032.Google ScholarCross Ref
- Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry. 2019. Adversarial examples are not bugs, they are features. arXiv preprint arXiv:1905.02175.Google Scholar
- Jake Lever, M. Krzywinski, Naomi S. Altman. Points of Significance: Regularization. Nature Methods, 13, 803-804.Google Scholar
- Nitish Srivastava, Geoffrey E. Hinton, A. Krizhevsky, Ilya Sutskever, R. Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 15, 1929-1958.Google ScholarDigital Library
- Hongyi Zhang, Moustapha Cissé, Yann Dauphin, David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412.Google Scholar
- Connor Shorten, T. Khoshgoftaar, T. 2019. A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6, 1-48.Google Scholar
- Yunchao Gong, Svetlana Lazebnik, Albert Gordo, and Florent Perronnin. 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 (2012), 2916–2929.Google Scholar
- Yair Weiss, Antonio Torralba, Robert Fergus, 2008. Spectral hashing. In Nips, Vol. 1. Citeseer, 4.Google Scholar
- O. Chapelle, J. Weston, L. Bottou. 2000. Vicinal Risk Minimization. NIPS.Google Scholar
Recommendations
Content Based Image Retrieval System Based on Deep Convolution Neural Network Model by Integrating Three-Fold Geometric Augmentation
AbstractDeep learning models depend on sizeable labelled training samples, and it is a common challenge that affects image retrieval based applications. Applications that are affected by these issues are computer vision and search engines. In the ...
Hierarchical deep hashing for image retrieval
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 ...
Deep reinforcement hashing with redundancy elimination for effective image retrieval
Highlights- Block-wise Hash Code Inference is utilized to preserve arbitrarily large global similarity relationship.
AbstractHashing is one of the most promising techniques in approximate nearest neighbor search due to its time efficiency and low cost in memory. Recently, with the help of deep learning, deep supervised hashing can perform representation ...
Comments