This Article 
 Bibliographic References 
 Add to: 
Learning to Relate Images
Aug. 2013 (vol. 35 no. 8)
pp. 1829-1846
Roland Memisevic, University of Montreal, Montreal
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. Recently, there has been increasing interest in learning to infer correspondences from data using relational, spatiotemporal, and bilinear variants of deep learning methods. These methods use multiplicative interactions between pixels or between features to represent correlation patterns across multiple images. In this paper, we review the recent work on relational feature learning, and we provide an analysis of the role that multiplicative interactions play in learning to encode relations. We also discuss how square-pooling and complex cell models can be viewed as a way to represent multiplicative interactions and thereby as a way to encode relations.
Index Terms:
Standards,Computational modeling,Training,Logic gates,Mathematical model,Image recognition,Learning systems,complex cells,Learning image relations,spatiotemporal features,mapping units,energy models
Roland Memisevic, "Learning to Relate Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1829-1846, Aug. 2013, doi:10.1109/TPAMI.2013.53
Usage of this product signifies your acceptance of the Terms of Use.