Abstract
In the study of media machine perception on image and video, people expect the machine to have the ability of lifelong learning like human. This paper, starting from anthropomorphic media perception, researches the multi-media perception which is based on lifelong machine learning. An ideal lifelong machine learning system for visual understanding is expected to learn relevant tasks from one or more domains continuously. However, most existing lifelong learning algorithms do not focus on the domain shift among tasks. In this work, we propose a novel cross-domain lifelong learning model (CD-LLM) to address the domain shift problem on visual understanding. The main idea is to generate a low-dimensional common subspace which captures domain invariable properties by embedding Grassmann manifold into tasks subspaces. With the low-dimensional common subspace, tasks can be projected and then model learning is performed. Extensive experiments are conducted on competitive cross-domain dataset. The results show the effectiveness and efficiency of the proposed algorithm on competitive cross-domain visual tasks.
This work is supported in part by the National Natural Science Founding of China under Grant 61171142 and Grant 61401163, Science and Technology Planning Project of Guangdong Province, China under Grant 2011A0108005, Grant 2014B010111003, Grant 2014B010111006 and Grant 2016B010108008, Guangzhou Key Lab of Body Data Science under Grant 201605030011, the Young Innovative Talent in High Education of Guangdong Province under Grant 2014KQNCX015 and the Fundamental Research Funds for the Central Universities under Grant 2015ZZ032.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Eaton, E., Ruvolo, P.L.: Ella: an efficient lifelong learning algorithm. In: ICML, pp. 507–515 (2013)
Thrun, S., O’Sullivan, J.: Discovering structure in multiple learning tasks: the TC algorithm. In: ICML, pp. 489–497 (1996)
Thrun, S.: Explanation-Based Neural Network Learning. Springer, New York (1996)
Silver, D.L., Alisch, R.: A measure of relatedness for selecting consolidated task knowledge. In: FLAIRS, pp. 399–404 (2005)
Silver, D.L., Mercer, R.E.: The parallel transfer of task knowledge using dynamic learning rates based on a measure of relatedness. Connect. Sci. Special Issue: Transf. Inductive Syst. 8(2), 277–294 (1996)
Silver, D.L., Mercer, R.E.: The task rehearsal method of life-long learning: overcoming impoverished data. In: Cohen, R., Spencer, B. (eds.) AI 2002. LNCS (LNAI), vol. 2338, pp. 90–101. Springer, Heidelberg (2002). doi:10.1007/3-540-47922-8_8
Silver, D.L., Yang, Q., Li, L.: Lifelong machine learning systems: beyond learning algorithms. In: AAAI Spring Symposium: Lifelong Machine Learning, pp. 49–55 (2013)
Mishra, M., Huan, J.: Learning task grouping using supervised task space partitioning in lifelong multitask learning. In: ACM CIKM, pp. 1091–1100 (2015)
Eaton, E., Ruvolo, P.L.: Active task selection for lifelong machine learning. In: AAAI (2013)
Alsharif, O., Bachman, P., Pineau, J.: Lifelong learning of discriminative representations. In: AAAI (2014)
Kumar, A., Daume III, H.: Learning task grouping and overlap in multi-task learning. arXiv preprint arXiv:1206.6417 (2012)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: IEEE ICCV, pp. 999–1006 (2011)
Chikuse, Y.: Procrustes analysis on the special manifolds. In: Springer Statistics on Special Manifolds. Lecture Notes in Statistics, vol. 174, pp. 231–246. Springer, New York (2003)
Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15561-1_16
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset (2007)
Bay, H., Tuytelaars, T., Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006). doi:10.1007/11744023_32
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.: Transfer feature learning with joint distribution adaptation. In: IEEE ICCV, pp. 2200–2207 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Qing, C., Huang, Z., Xu, X. (2016). A Cross-Domain Lifelong Learning Model for Visual Understanding. In: Chen, E., Gong, Y., Tie, Y. (eds) Advances in Multimedia Information Processing - PCM 2016. PCM 2016. Lecture Notes in Computer Science(), vol 9916. Springer, Cham. https://doi.org/10.1007/978-3-319-48890-5_43
Download citation
DOI: https://doi.org/10.1007/978-3-319-48890-5_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48889-9
Online ISBN: 978-3-319-48890-5
eBook Packages: Computer ScienceComputer Science (R0)