Boosted Cross-Domain Dictionary Learning for Visual Categorization

In an extension of the AdaBoost and transfer AdaBoost algorithms, a boosted cross-domain categorization framework works with a learned domain-adaptive dictionary pair and boosted classifiers so that both the auxiliary domain data representations and their distributions are optimized to match the target domain. By iteratively updating weak classifiers, the categorization system allocates more credits to "similar"' auxiliary domain samples, while abandoning "dissimilar" auxiliary domain samples. The authors evaluated the proposed approach using multiple transfer learning scenarios, including image classification, human action recognition, and 3D object recognition. The proposed method consistently outperformed the state-of-the-art methods in all the evaluated scenarios.

Authors

• Fan Zhu
• Ling Shao Terminus Group
• Yi Fang

Keywords

• Learning systems
• Classification
• Visualization
• Knowledge transfer
• Data transfer
• Image reconstruction
• Visual Classification
• Dictionary Learning
• Training Data
• Learning Algorithms
• Computer Vision
• Learning Framework
• Super-resolution
• Transfer Learning
• Learning System
• Action Recognition
• Image Patches
• Target Domain
• Sparse Representation
• Auxiliary Data
• Training Instances
• Biclusters
• Human Activity Recognition
• Insufficient Training Data
• Visual Representation Of Data
• Action Recognition Task
• Source Domain Data
• Source Domain
• Sparse Coding
• Equivalent Optimization Problem
• Number Of Images
• Local Features
• Difference Of Gaussian
• Depth Images
• Training Images
• intelligent systems
• boosting
• visual categorization