OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Label-consistent sparse auto-encoders

Rolland, Thomas and Basarab, Adrian and Pellegrini, Thomas Label-consistent sparse auto-encoders. (2019) In: Workshop on Signal Processing with Adaptative Sparse Structured Representations (SPARS 2019), 1 July 2019 - 4 July 2019 (Toulouse, France).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
184kB

Abstract

Auto-encoders (AE) is a particular type of unsupervised neural networks that aim at providing a compact representation of a signal or an image [1]. Such AEs are useful for data compression but most of the time the representations they provide are not appropriate as is for a downstream classification task. This is due to the fact that they are trained to minimize a reconstruction error and not a classification loss. Classification attempts with AEs have already been proposed such as contractive AEs [2], correspondence AEs [3] and stacked similarity-aware AEs [4], for instance. Inspired by label-consistent K-SVD (LC-KSVD) [5], we propose a novel supervised version of AEs that integrates class information within the encoded representations.

Item Type:Conference or Workshop Item (Paper)
HAL Id:hal-02419439
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Other partners > Instituto de Engenharia de Sistemas e Computadores - Investigação e Desenvolvimento - INESC-ID (PORTUGAL)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Laboratory name:
Funders:
AMIES : Agence pour les Mathématiques en Interaction avec l'Entreprise et la Société (France) - ANR : Agence nationale de la recherche (France)
Statistics:download
Deposited On:06 Dec 2019 15:33

Repository Staff Only: item control page