Deep Network Classification by Scattering and Homotopy Dictionary Learning
| Autor: | Zarka, John, Thiry, Louis, Angles, Tomás, Mallat, Stephane |
|---|---|
| Přispěvatelé: | Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), Collège de France - Chaire Sciences des données, Collège de France (CdF (institution)), This work was supported by the ERC InvariantClass 320959, grants from Région Ile-de-France and the PRAIRIE 3IA Institute of the French ANR-19-P3IA-0001 program. We thank the Scientific Computing Core at the Flatiron Institute for the use of their computing resources. We would like to thank Eugene Belilovsky for helpful discussions and comments., ANR-19-P3IA-0001,PRAIRIE,PaRis Artificial Intelligence Research InstitutE(2019), École normale supérieure - Paris (ENS Paris), Chaire Sciences des données, Zarka, John, PaRis Artificial Intelligence Research InstitutE - - PRAIRIE2019 - ANR-19-P3IA-0001 - P3IA - VALID, Département d'informatique de l'École normale supérieure (DI-ENS) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Statistics - Machine Learning Computer Vision and Pattern Recognition (cs.CV) [INFO.INFO-NE] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] Computer Science - Computer Vision and Pattern Recognition Machine Learning (stat.ML) [INFO]Computer Science [cs] [INFO] Computer Science [cs] [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] Machine Learning (cs.LG) |
| Zdroj: | ICLR 2020-8th International Conference on Learning Representations ICLR 2020-8th International Conference on Learning Representations, Apr 2020, Addis Ababa / Virtual, Ethiopia |
| Popis: | International audience; We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a higher classification accuracy than AlexNet over the ImageNet 2012 dataset. The network first applies a scattering transform that linearizes variabilities due to geometric transformations such as translations and small deformations. A sparse l1 dictionary coding reduces intra-class variability while preserving class separation through projections over unions of linear spaces. It is implemented in a deep convolutional network with a homotopy algorithm having an exponential convergence. A convergence proof is given in a general framework that includes ALISTA. Classification results are analyzed on ImageNet. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|