HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Rotation-invariant NN for learning naturally un-oriented data

Abstract : Deep convolutional neural networks accuracy is heavily impacted by the rotations of the input data. In this paper, we propose a convolutional predictor that is invariant to rotations in the input. This architecture is capable of predicting the angular orientation without angle-annotated data. Furthermore, the predictor maps continuously the random rotation of the input to a circular space of the prediction. For this purpose, we use the roto-translation properties existing in the Scattering Transform Networks with a series of 3D Convolutions. We validate the results by training with upright and randomly rotated samples. This allows further applications of this work on fields like automatic re-orientation of randomly oriented datasets.
Complete list of metadata

Contributor : Rosemberg Rodriguez Salas Connect in order to contact the contributor
Submitted on : Monday, February 18, 2019 - 11:26:00 AM
Last modification on : Saturday, January 15, 2022 - 3:58:29 AM
Long-term archiving on: : Sunday, May 19, 2019 - 2:05:14 PM


Files produced by the author(s)


  • HAL Id : hal-02022802, version 1


Rosemberg Rodriguez Salas, Petr Dokládal, Eva Dokladalova. Rotation-invariant NN for learning naturally un-oriented data. 2019. ⟨hal-02022802⟩



Record views


Files downloads