Conference Papers Year : 2023

Learning on entropy coded images with CNN

Abstract

We propose an empirical study to see whether learning with convolutional neural networks (CNNs) on entropy coded data is possible. First, we define spatial and semantic closeness, two key properties that we experimentally show to be necessary to guarantee the efficiency of the convolution. Then, we show that these properties are not satisfied by the data processed by an entropy coder. Despite this, our experimental results show that learning in such difficult conditions is still possible, and that the performance are far from a random guess. These results have been obtained thanks to the construction of CNN architectures designed for 1D data (one based on VGG, the other on ResNet). Finally, we propose some experiments that explain why CNN are still performing reasonably well on entropy coded data.
Fichier principal
Vignette du fichier
icassp2023_learning_on_entropy_coded_images_with_cnn.pdf (199.78 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04133662 , version 1 (20-06-2023)

Licence

Identifiers

Cite

Rémi Piau, Thomas Maugey, Aline Roumy. Learning on entropy coded images with CNN. ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10095647⟩. ⟨hal-04133662⟩
38 View
199 Download

Altmetric

Share

More