Abstract
Cross-modality matching refers to the problem of comparing similarity/dissimilarity of a pair of data points of different modalities, such as an image and a text. Deep neural networks have been popular to represent data points of different modalities due to their ability to extract effective features. However, existing works use simple distance metrics to compare the deep features of multiple modalities, which do not fit the nature of cross-modality matching, because it imposes the features of different modalities to be of the same dimension and do not allow cross-feature matching. To solve this problem, we propose to use convolutional neural network (CNN) models with soft-max activation layer to represent a pair of different-modality data points to two histograms (not necessarily of the same dimensions) and compare their dissimilarity by using earth mover’s distance (EMD). The EMD can match the features extracted by the two CNN models of different modalities freely. Moreover, we develop a joint learning framework to learn the CNN parameters specifically for the EMD-driven comparison, supervised by the relevance/irrelevance labels of the data pairs of different modalities. The experiments over applications such as image–text retrieval, and malware detection show its advantage over existing cross-modality matching methods.
Similar content being viewed by others
References
Boyd S, Parikh N, Chu E, Peleato B, Eckstein J et al (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends® Mach Learn 3(1):1–122
Bronstein MM, Bronstein AM, Michel F, Paragios N (2010) Data fusion through cross-modality metric learning using similarity-sensitive hashing. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR), pp 3594–3601. IEEE
Chua TS, Tang J, Hong R, Li H, Luo Z, Zheng Y (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. ACM, p 48
Graves A, Mohamed A, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), 2013. IEEE, pp 6645–6649
Jia Y, Salzmann M, Darrell T (2011) Learning cross-modality similarity for multinomial data. In: 2011 IEEE international conference on computer vision (ICCV). IEEE, pp 2407–2414
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Lawrence S, Giles CL, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8(1):98–113
Lin L, Wang G, Zuo W, Feng X, Zhang L (2017) Cross-domain visual matching via generalized similarity measure and feature learning. IEEE Trans Pattern Anal Mach Intell 39(6):1089–1102
Ling H, Okada K (2007) An efficient earth mover’s distance algorithm for robust histogram comparison. IEEE Trans Pattern Anal Mach Intell 29(5):840–853
Masci J, Bronstein MM, Bronstein AM, Schmidhuber J (2014) Multimodal similarity-preserving hashing. IEEE Trans Pattern Anal Mach Intell 36(4):824–830
Mikolov T, Karafiát M, Burget L, Černockỳ J, Khudanpur S (2010) Recurrent neural network based language model. In: Eleventh annual conference of the international speech communication association
Plummer BA, Wang L, Cervantes CM, Caicedo JC, Hockenmaier J, Lazebnik S (2015) Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: 2015 IEEE international conference on computer vision (ICCV). IEEE, pp 2641–2649
Rubner Y, Tomasi C (2001) The earth mover’s distance. In: Rubner Y, Tomasi C (eds) Perceptual metrics for image database navigation. Springer, Berlin, pp 13–28
Rubner Y, Tomasi C, Guibas LJ (2000) The earth mover’s distance as a metric for image retrieval. Int J Comput Vis 40(2):99–121
Sandler R, Lindenbaum M (2011) Nonnegative matrix factorization with earth mover’s distance metric for image analysis. IEEE Trans Pattern Anal Mach Intelligence 33(8):1590–1602
Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Netw 20(1):61–80
Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673–2681
Shishibori M, Koizumi D, Kita K (2009) A fast retrieval algorithm for the earth mover’s distance using EMD lower bounds and the priority queue. In: International conference on natural language processing and knowledge engineering, 2009. NLP-KE 2009. IEEE, pp 1–6
Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In: Null. IEEE, p 958
Wang L, Li Y, Huang J, Lazebnik S (2018) Learning two-branch neural networks for image-text matching tasks. IEEE Trans Pattern Anal Mach Intell 41:394–407
Wu Y, Wang L, Cui F, Zhai H, Dong B, Wang JY (2016) Cross-model convolutional neural network for multiple modality data representation. Neural Comput Appl 30:1–11
Zhang G, Liang G, Su F, Qu F, Wang JY (2018) Cross-domain attribute representation based on convolutional neural network. In: International conference on intelligent computing. Springer, pp 134–142
Zhang H, Chow TW (2011) A coarse-to-fine framework to efficiently thwart plagiarism. Pattern Recognit 44(2):471–487
Acknowledgements
This work was partly supported by the National Key Technology R&D Program of China (Grant No. 2017YFB0802900).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zuo, Z., Liu, L., Liu, J. et al. Cross-modality earth mover’s distance-driven convolutional neural network for different-modality data. Neural Comput & Applic 32, 9581–9592 (2020). https://doi.org/10.1007/s00521-019-04471-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-019-04471-8