Robust Image Analysis by L1-Norm Semi-supervised Learning
Preprint
Abstract
This paper presents a novel L1-norm semi-supervised learning algorithm for robust image analysis by giving new L1-norm formulation of Laplacian regularization which is the key step of graph-based semi-supervised learning. Since our L1-norm Laplacian regularization is defined directly over the eigenvectors of the normalized Laplacian matrix, we successfully formulate semi-supervised learning as an L1-norm linear reconstruction problem which can be effectively solved with sparse coding. By working with only a small subset of eigenvectors, we further develop a fast sparse coding algorithm for our L1-norm semi-supervised learning. Due to the sparsity induced by sparse coding, the proposed algorithm can deal with the noise in the data to some extent and thus has important applications to robust image analysis, such as noise-robust image classification and noise reduction for visual and textual bag-of-words (BOW) models. In particular, this paper is the first attempt to obtain robust image representation by sparse co-refinement of visual and textual BOW models. The experimental results have shown the promising performance of the proposed algorithm.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Spatial Markov Kernels for Image Categorization and AnnotationIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2011
- Local features are not lonely – Laplacian sparse coding for image classification2010
- Combining Context, Consistency, and Diversity Cues for Interactive Image CategorizationIEEE Transactions on Multimedia, 2010
- Semi-Supervised Bilinear Subspace LearningIEEE Transactions on Image Processing, 2009
- Subspace Pursuit for Compressive Sensing Signal ReconstructionIEEE Transactions on Information Theory, 2009
- Image annotation via graph learningPattern Recognition, 2009
- Robust Face Recognition via Sparse RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Gradient Projection for Sparse Reconstruction: Application to Compressed Sensing and Other Inverse ProblemsIEEE Journal of Selected Topics in Signal Processing, 2007
- Label Propagation through Linear NeighborhoodsIEEE Transactions on Knowledge and Data Engineering, 2007
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solutionCommunications on Pure and Applied Mathematics, 2006