Scattering Networks for Hybrid Representation Learning
Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning ta...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 41(2019), 9 vom: 17. Sept., Seite 2208-2221
|
|---|
| 1. Verfasser: |
Oyallon, Edouard
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zagoruyko, Sergey,
Huang, Gabriel,
Komodakis, Nikos,
Lacoste-Julien, Simon,
Blaschko, Matthew,
Belilovsky, Eugene |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2019
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|