Learning About Multiple Objects in Images: Factorial Learning without Factorial Search

Christopher K. I. Williams, Michalis K. Titsias
2002 Neural Information Processing Systems  
We consider data which are images containing views of multiple objects. Our task is to learn about each of the objects present in the images. This task can be approached as a factorial learning problem, where each image must be explained by instantiating a model for each of the objects present with the correct instantiation parameters. A major problem with learning a factorial model is that as the number of objects increases, there is a combinatorial explosion of the number of configurations
more » ... t need to be considered. We develop a method to extract object models sequentially from the data by making use of a robust statistical method, thus avoiding the combinatorial explosion, and present results showing successful extraction of objects from real images. For both methods we need to adapt the model presented in section 2.1. The problem is that occlusion can occur of both the foreground and the background. For a foreground pixel, a different object to the one being modelled may be interposed between the camera and our object, thus perturbing the pixel value. This can be modelled with a mixture distribution as
dblp:conf/nips/WilliamsT02 fatcat:2t6wv4c5dbhcjiixsd6zxy6kem