Abstract
Learning representations invariant to image transformations is fundamental to improving object recognition. We explore the connections between i-theory, Toroidal Subspace Analysis and slow subspace learning. All these methods can only achieve invariance to one transformation. Motivated by this limitation of these global methods we adapt the slow subspace approach to a local convolutional setting. Experimentally we show invariance to multiple transformations, and test object recognition performance.
Originalsprache | Englisch |
---|---|
Titel | Workshop New Challenges in Neural Computation 2015 |
Redakteure/-innen | Barbara Hammer, Thomas Villmann |
Seitenumfang | 9 |
Band | 03 |
Erscheinungsdatum | 2015 |
Seiten | 16-24 |
Publikationsstatus | Veröffentlicht - 2015 |
Veranstaltung | 37th German Conference on Pattern Recognition - Workshop Program: New Challenges in Neural Computation (NC2) - RWTH Aachen, Aachen, Deutschland Dauer: 10.10.2015 → 10.10.2015 http://vmv2015.rwth-aachen.de/workshops.html |