Next Article in Journal
Microstructure and Thermoelectric Properties of (Bi0.48Sb1.52)Te3 Thick Films Prepared with Tape Casting Method
Next Article in Special Issue
Bi-Objective Workflow Scheduling on Heterogeneous Computing Systems Using a Memetic Algorithm
Previous Article in Journal
Translating Sentimental Statements Using Deep Learning Techniques
Article

Rotation Invariant Networks for Image Classification for HPC and Embedded Systems

1
LIGM, University Gustave Eiffel, CNRS, ESIEE Paris, F-77454 Marne-la-Vallée, France
2
Center for Mathematical Morphology, MINES Paris—PSL Research University, 77300 Fontainebleau, France
*
Author to whom correspondence should be addressed.
Electronics 2021, 10(2), 139; https://doi.org/10.3390/electronics10020139
Received: 14 December 2020 / Revised: 5 January 2021 / Accepted: 6 January 2021 / Published: 10 January 2021
Convolutional Neural Network (CNNs) models’ size reduction has recently gained interest due to several advantages: energy cost reduction, embedded devices, and multi-core interfaces. One possible way to achieve model reduction is the usage of Rotation-invariant Convolutional Neural Networks because of the possibility of avoiding data augmentation techniques. In this work, we present the next step to obtain a general solution to endowing CNN architectures with the capability of classifying rotated objects and predicting the rotation angle without data-augmentation techniques. The principle consists of the concatenation of a representation mapping transforming rotation to translation and a shared weights predictor. This solution has the advantage of admitting different combinations of various basic, existing blocks. We present results obtained using a Gabor-filter bank and a ResNet feature backbone compared to previous other solutions. We also present the possibility to select between parallelizing the network in several threads for energy-aware High Performance Computing (HPC) applications or reducing the memory footprint for embedded systems. We obtain a competitive error rate on classifying rotated MNIST and outperform existing state-of-the-art results on CIFAR-10 when trained on up-right examples and validated on random orientations. View Full-Text
Keywords: CNN; classification; rotation invariance; angular prediction; model reduction CNN; classification; rotation invariance; angular prediction; model reduction
Show Figures

Figure 1

MDPI and ACS Style

Rodriguez Salas, R.; Dokladal, P.; Dokladalova, E. Rotation Invariant Networks for Image Classification for HPC and Embedded Systems. Electronics 2021, 10, 139. https://doi.org/10.3390/electronics10020139

AMA Style

Rodriguez Salas R, Dokladal P, Dokladalova E. Rotation Invariant Networks for Image Classification for HPC and Embedded Systems. Electronics. 2021; 10(2):139. https://doi.org/10.3390/electronics10020139

Chicago/Turabian Style

Rodriguez Salas, Rosemberg, Petr Dokladal, and Eva Dokladalova. 2021. "Rotation Invariant Networks for Image Classification for HPC and Embedded Systems" Electronics 10, no. 2: 139. https://doi.org/10.3390/electronics10020139

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop