Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

By Li Fei-Fei, Rob Fergus, Pietro Perona. 2004

5,814 citations recorded by the source corpus.

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 more than a handful of object categories. We present an method for learning object categories from just a few training images. It is quick and it uses prior information in a principled way. We test it on a dataset composed of images of objects belonging to 101 widely varied categories. Our proposed method is based on making use of prior information, assembled from (unrelated) object categories which were previously learnt. A generative probabilistic model is used, which represents the shape and appearance of a constellation of features belonging to the object. The parameters of the model are learnt incrementally in a Bayesian manner. Our incremental algorithm is compared experimentally to an earlier batch Bayesian algorithm, as well as to one based on maximum-likelihood. The incremental and batch versions have comparable classification performance on small training sets, but incremental learning is significantly faster, making real-time learning feasible. Both Bayesian methods outperform maximum likelihood on small training sets.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Generative Models, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Xiaogang Wang
  5. Ming-Hsuan Yang
  6. Jitendra Malik
  7. Andrew Zisserman
  8. Yi Yang

In Media Technology

  1. Andrew Zisserman
  2. Luc Van Gool
  3. Ming-Hsuan Yang
  4. Andrea Vedaldi
  5. Li Fei-Fei
  6. Antonio Torralba
  7. Alexei A. Efros
  8. Jitendra Malik

In Generative Models

  1. Yoshua Bengio
  2. Jun-Yan Zhu
  3. Stefano Ermon
  4. Eli Shechtman
  5. Alexei A. Efros
  6. Richard Zhang
  7. Sergey Levine
  8. Ming-Hsuan Yang

In Optimization & Training

  1. Quoc V. Le
  2. Yoshua Bengio
  3. Francis R. Bach
  4. Michael I. Jordan
  5. Simon Lacoste-Julien
  6. Julien Mairal
  7. Yann LeCun
  8. Trevor Darrell

Citations in the corpus