Greedy Learning of Multiple Objects in Images Using Robust Statistics and Factorial Learning
- 1 May 2004
- journal article
- Published by MIT Press in Neural Computation
- Vol. 16 (5), 1039-1062
- https://doi.org/10.1162/089976604773135096
Abstract
We consider data that 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 that 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.Keywords
This publication has 6 references indexed in Scilit:
- Transformation-invariant clustering using the EM algorithmIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Learning the parts of objects by non-negative matrix factorizationNature, 1999
- Are object shape primitives learnable?Neurocomputing, 1999
- Representing moving images with layersIEEE Transactions on Image Processing, 1994
- Unsupervised LearningNeural Computation, 1989
- Optimal unsupervised learning in a single-layer linear feedforward neural networkNeural Networks, 1989