Laplacian Affinity Propagation for Semi-Supervised Object Classification

• Published in: 2007 IEEE International Conference on Image Processing Vol. 1; pp. I - 189 - I - 192
• Main Authors: Yun Fu, Zhu Li, Xi Zhou, Huang, T.S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2007
• Subjects: Closed-form solution; Clustering algorithms; graph embedding; Information retrieval; Labeling; Laplace equations; Learning systems; local affinity; object classification; Pattern recognition; Semi-supervised learning; Semisupervised learning; spectral clustering; Training data

We solve the semi-supervised multi-class object classification problem by a graph-based learning algorithm, called Laplacian affinity propagation (LAP). The idea is to model and train both labeled and unlabeled data by constructing a local neighborhood affinity graph in a smoothness formulation of L...