A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories

Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing hundreds of parameters. We present a method for learning object categories from just a few images (? ). It is based on incorporating `generic' knowledge which may be obtained from previously learnt models of unrelated categories. We operate in a variational Bayesian framework: object categories are represented by probabilistic models, and `prior' knowledge is represented as a probability density function on the parameters of these models. The `posterior' model for an object category is obtained by updating the prior in the light of one or more observations. Our ideas are demonstrated on four diverse categories (human faces, airplanes, motorcycles, spotted cats). Initially three categories are learned from hundreds of training examples, and a "prior" is estimated from the...

• Type: Conference
• Year: 2003
• Where: ICCV
• Authors: Fei-Fei Li 0002, Robert Fergus, Pietro Perona
• Keywords: Computer Vision, ICCV 2003, Models Containing Hundreds, Object Categories, Object Category, Training Examples, Unrelated Categories