Abstract
Recently, domain adaptation has gained great popularity, while most researchers are focusing on domains in homogenous modalities, e.g., image domains. In reality, heterogeneous domains are pretty common and more challenging. In this paper, we present MCD-JD—a Maximum Classifier Discrepancy model which considers the joint distribution of the source and target domain data for heterogeneous domain adaption. MCD-JD derives from Generative Adversarial Networks (GAN) consisting of two parts, i.e., minimizing the discrepancy of joint distribution, and maximizing classifier discrepancy. Specifically, the first part uses the Maximum Mean Discrepancy (MMD) regularization to adapt the data distributions between source and target domains. The second part utilizes two different classifiers to maximize their discrepancy of making predictions on the target domain data, which further minimizes the discrepancy of data distributions between source and target domains. We collect a dataset depicting real-world events (e.g., protests, explosions, etc.) from multiple heterogeneous data domains, including news media textual articles, social media (Flickr) images, and YouTube videos. Extensive experiments conducted on the real-world dataset manifest the effectiveness of MCD-JD, which outperforms state-of-the-art benchmark models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Hsieh, L.C., Hsu, W.H.: Search-based automatic image annotation via flickr photos using tag expansion. In: ICASSP, pp. 2398–2401 (2010)
Ginsca, A.L., Popescu, A., Le Borgne, H., Ballas, N., Vo, P., Kanellos, I.: Large-scale image mining with flickr groups. In: He, X., Luo, S., Tao, D., Xu, C., Yang, J., Hasan, M.A. (eds.) MMM 2015. LNCS, vol. 8935, pp. 318–334. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-14445-0_28
Yang, Z., Li, Q., Liu, W., Ma, Y., Cheng, M.: Dual graph regularized NMF model for social event detection from Flickr data. World Wide Web 20, 995–1015 (2017)
Yang, Z., Li, Q., Lu, Z., Ma, Y., Gong, Z., Liu, W.: Dual structure constrained multimodal feature coding for social event detection from Flickr data. ACM Trans. Internet Technol. (TOIT) 17, 19 (2017)
Kumaran, G., Allan, J.: Text classification and named entities for new event detection. In: Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 297–304 ACM (2004)
Weng, J., Lee, B.S.: Event detection in Twitter. In: ICWSM, pp. 401–408 (2011)
Zaharieva, M., Zeppelzauer, M., Breiteneder, C.: Automated social event detection in large photo collections. In: Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval, pp. 167–174 ACM (2013)
Firan, C.S., Georgescu, M., Nejdl, W., Paiu, R.: Bringing order to your photos: event-driven classification of flickr images based on social knowledge. In: Proceedings of the 19th ACM International Conference on Information and Knowledge Management, pp. 189–198 ACM (2010)
Ye, G., Li, Y., Xu, H., Liu, D., Chang, S.F.: Eventnet: a large scale structured concept library for complex event detection in video. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 471–480 ACM (2015)
Abhik, D., Toshniwal, D.: Sub-event detection during natural hazards using features of social media data. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 783–788 ACM (2013)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Computer Vision and Pattern Recognition (CVPR) (2018)
Sejdinovic, D., Sriperumbudur, B., Gretton, A., Fukumizu, K.: Equivalence of distance-based and RKHS-based statistics in hypothesis testing. Ann. Stat. 41, 2263–2291 (2013)
Allan, J., Papka, R., Lavrenko, V.: On-line new event detection and tracking. In: Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 37–45. ACM (1998)
Wei, C., Lee, Y.: Event detection from online news documents for supporting environmental scanning. Decis. Support Syst. 36, 385–401 (2004)
Petrovic, S., Osborne, M., and Lavrenko, V.: Streaming first story detection with application to Twitter. In: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, HLT 2010, pp. 181–189 (2010)
Sakaki, T., Okazaki, M., Matsuo, Y.: Earthquake shakes Twitter users: real-time event detection by social sensors. In: Proceedings of the 19th International Conference on World Wide Web, pp. 851–860. ACM (2010)
Chen, L., Roy, A.: Event detection from flickr data through wavelet-based spatial analysis. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp. 523–532 ACM (2009)
Petkos, G., et al.: Social event detection at MediaEval: a three-year retrospect of tasks and results. In: Proceedings ACM ICMR 2014 Workshop on Social Events in Web Multimedia (2014)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345–1359 (2010)
Long, M., Wang, J., Ding, G., Sun, J., Philip, S.Y.: Transfer feature learning with joint distribution adaptation. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 2200–2207. IEEE (2013)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13, 723–773 (2012)
Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: AAAI, p. 8 (2016)
Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97–105 (2015)
Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_35
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: International Conference on Machine Learning, pp. 2208–2217 (2017)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 2030–2096 (2016)
Shen, J., Qu, Y., Zhang, W., Yu, Y.: Adversarial representation learning for domain adaptation. arXiv preprint arXiv:1707.01217 (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Borgwardt, K.M., Gretton, A., Rasch, M.J., Kriegel, H.P., Schölkopf, B., Smola, A.J.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22, e49–e57 (2006)
Daras, P., Manolopoulou, S., Axenopoulos, A.: Search and retrieval of rich media objects supporting multiple multimodal queries. IEEE Trans. Multimed. 14, 734–746 (2012)
Kiros, R., et al.: Skip-thought vectors. In: Advances in Neural Information Processing Systems, pp. 3294–330 (2015)
Zhu, Y., et al.:Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 19–27 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems, pp. 153–160 (2007)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference Computer Vision and Pattern Recognition (CVPR), pp. 2066–2073. IEEE (2012)
Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (No. 61703109, No. 91748107, No.U1611461), the Guangdong Innovative Research Team Program (No. 2014ZT05G157), Science and Technology Program of Guangdong Province, China (No. 2016A010101012), and CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, 100190, Beijing, China. (No. CASNDST201703), and an internal grant from City University of Hong Kong (project no. 9610367).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, Z. et al. (2018). Improving Maximum Classifier Discrepancy by Considering Joint Distribution for Domain Adaptation. In: Hacid, H., Cellary, W., Wang, H., Paik, HY., Zhou, R. (eds) Web Information Systems Engineering – WISE 2018. WISE 2018. Lecture Notes in Computer Science(), vol 11234. Springer, Cham. https://doi.org/10.1007/978-3-030-02925-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-02925-8_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-02924-1
Online ISBN: 978-3-030-02925-8
eBook Packages: Computer ScienceComputer Science (R0)