A Cross-Domain Lifelong Learning Model for Visual Understanding

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.

[1]  Eric Eaton,et al.  Active Task Selection for Lifelong Machine Learning , 2013, AAAI.

[2]  Sebastian Thrun,et al.  Discovering Structure in Multiple Learning Tasks: The TC Algorithm , 1996, ICML.

[3]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[4]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[5]  Rama Chellappa,et al.  Domain adaptation for object recognition: An unsupervised approach , 2011, 2011 International Conference on Computer Vision.

[6]  Qiang Yang,et al.  Lifelong Machine Learning Systems: Beyond Learning Algorithms , 2013, AAAI Spring Symposium: Lifelong Machine Learning.

[7]  Philip S. Yu,et al.  Transfer Feature Learning with Joint Distribution Adaptation , 2013, 2013 IEEE International Conference on Computer Vision.

[8]  Daniel L. Silver,et al.  The Parallel Transfer of Task Knowledge Using Dynamic Learning Rates Based on a Measure of Relatedness , 1996, Connect. Sci..

[9]  Hal Daumé,et al.  Learning Task Grouping and Overlap in Multi-task Learning , 2012, ICML.

[10]  Philip Bachman,et al.  Lifelong Learning of Discriminative Representations , 2014, ArXiv.

[11]  Jun Huan,et al.  Learning Task Grouping using Supervised Task Space Partitioning in Lifelong Multitask Learning , 2015, CIKM.

[12]  Sebastian Thrun,et al.  Explanation-based neural network learning a lifelong learning approach , 1995 .

[13]  Daniel L. Silver,et al.  A Measure of Relatedness for Selecting Consolidated Task Knowledge , 2005, FLAIRS Conference.

[14]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[15]  Robert E. Mercer,et al.  The Task Rehearsal Method of Life-Long Learning: Overcoming Impoverished Data , 2002, Canadian Conference on AI.

[16]  Y. Chikuse,et al.  Procrustes analysis on some special manifolds , 1999 .

[17]  Sebastian Thrun,et al.  Explanation-based neural network learning , 1996 .

[18]  Robert E. Mercer,et al.  The Parallel Transfer of Task Knowledge Using Dynamic Learning Rates Based on a Measure of Relatedness , 1998, Learning to Learn.

[19]  Eric Eaton,et al.  ELLA: An Efficient Lifelong Learning Algorithm , 2013, ICML.