Skip to Main content Skip to Navigation
Conference papers

Rotation invariant CNN using scattering transform for image classification

Abstract : Deep convolutional neural networks accuracy is heavily impacted by 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 : Eva Dokladalova Connect in order to contact the contributor
Submitted on : Thursday, May 20, 2021 - 1:25:28 PM
Last modification on : Wednesday, November 17, 2021 - 12:27:19 PM


Files produced by the author(s)


  • HAL Id : hal-02008378, version 2
  • ARXIV : 2105.10175


Rosemberg Rodriguez Salas, Eva Dokladalova, Petr Dokládal. Rotation invariant CNN using scattering transform for image classification. IEEE International Conference on Image Processing (ICIP), Sep 2019, Taipei, Taiwan. ⟨hal-02008378v2⟩



Record views


Files downloads