Name
Abstract | ||
|---|---|---|
A fundamental operation in many vision tasks, including motion understanding, stereopsis, visual odometry, or invariant recognition, is establishing correspondences between images or between images and data from other modalities. We present an analysis of the role that multiplicative interactions play in learning such correspondences, and we show how learning and inferring relationships between images can be viewed as detecting rotations in the eigenspaces shared among a set of orthogonal matrices. We review a variety of recent multiplicative sparse coding methods in light of this observation. We also review how the squaring operation performed by energy models and by models of complex cells can be thought of as a way to implement multiplicative interactions. This suggests that the main utility of including complex cells in computational models of vision may be that they can encode relations not invariances. |
Year | Venue | Keywords |
|---|---|---|
2011 | arXiv: Computer Vision and Pattern Recognition | pattern recognition,artificial intelligent,sparse coding,computer model,visual odometry |
Field | DocType | Volume |
Multiplicative function,Visual odometry,Stereopsis,Computer science,Artificial intelligence,ENCODE,Computer vision,Orthogonal matrix,Pattern recognition,Neural coding,Computational model,Invariant (mathematics),Machine learning | Journal | abs/1110.0107 |
Citations | PageRank | References |
2 | 0.43 | 10 |
Authors | ||
1 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Roland Memisevic | 1 | 1116 | 65.87 |