Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories

• Published in: Computer vision and image understanding Vol. 106; no. 1; pp. 59 - 70
• Main Authors: Fei-Fei, Li, Fergus, Rob, Perona, Pietro
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.04.2007
• Subjects: Bayesian model; Categorization; Generative model; Incremental learning; Object recognition; Incremental learning; Object recognition; Bayesian model; Categorization; Generative model

Current computational approaches to learning visual object categories require thousands of training images, are slow, cannot learn in an incremental manner and cannot incorporate prior information into the learning process. In addition, no algorithm presented in the literature has been tested on mor...