Multiview Vector-Valued Manifold Regularization for Multilabel Image Classification

• Published in: IEEE transaction on neural networks and learning systems Vol. 24; no. 5; pp. 709 - 722
• Main Authors: Luo, Yong, Tao, Dacheng, Xu, Chang, Xu, Chao, Liu, Hong, Wen, Yonggang
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.05.2013; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Correlation; Data processing. List processing. Character string processing; Database Management Systems; Exact sciences and technology; Image classification; Image color analysis; Image Interpretation, Computer-Assisted; Kernel; Labels; Laplace equations; manifold; Manifolds; Memory organisation. Data processing; Models, Statistical; multilabel; multiview; Neural networks; Neural Networks (Computer); Optimization; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Regularization; Reproducibility of Results; semisupervised; Software; Support vector machines; Surface layer; Texture; multiview; Computer vision; Tree(graph); Image processing; Multi-label classification; Pedestrian; semisupervised; Bicycle; Texture; Color image; Multiple image; Multiple view; Walking; multilabel; Manifold; Efficiency; Semi-supervised learning; Regularization; Image classification
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2013.2238682

In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e.g., pedestrian, bicycle, and tree) and is properly characterized by multiple visual features (e.g., color, texture, and shape). Currently, available tools ignore either the label relationship or the view complementarily. Motivated by the success of the vector-valued function that constructs matrix-valued kernels to explore the multilabel structure in the output space, we introduce multiview vector-valued manifold regularization (MV 3 MR) to integrate multiple features. MV 3 MR exploits the complementary property of different features and discovers the intrinsic local geometry of the compact support shared by different features under the theme of manifold regularization. We conduct extensive experiments on two challenging, but popular, datasets, PASCAL VOC' 07 and MIR Flickr, and validate the effectiveness of the proposed MV 3 MR for image classification.