RED-NN: Rotation-Equivariant Deep Neural Network for Classification and Prediction of Rotation - École des Ponts ParisTech Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

RED-NN: Rotation-Equivariant Deep Neural Network for Classification and Prediction of Rotation

Résumé

In this work, we propose a new Convolutional Neural Network (CNN) for classification of rotated objects. This architecture is built around an ordered ensemble of oriented edge detectors to create a roto-translational space that transforms the input rotation into translation. This space allows the subsequent predictor to learn the internal spatial and angular relations of the objects regardless of their orientation. No data augmentation is needed and the model remains significantly smaller. It presents a self-organization capability and learns to predict the class and the rotation angle without requiring an angle-labeled dataset. We present the results of training with both upright and randomly rotated datasets. The accuracy outperforms the current state of the art on upright oriented training.
Fichier principal
Vignette du fichier
RotCNN.pdf (684.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02170933 , version 1 (02-07-2019)

Identifiants

  • HAL Id : hal-02170933 , version 1

Citer

Rosemberg Rodriguez Salas, Petr Dokládal, Eva Dokladalova. RED-NN: Rotation-Equivariant Deep Neural Network for Classification and Prediction of Rotation. 2019. ⟨hal-02170933⟩
6766 Consultations
793 Téléchargements

Partager

Gmail Facebook X LinkedIn More