Processing Energy Modeling for Neural Network Based Image Compression

Herglotz C, Brand F, Regensky A, Rievel F, Kaup A (2023)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Event location: Kuala Lumpur

URI: https://arxiv.org/abs/2306.16755

Abstract

Nowadays, the compression performance of neural-networkbased
image compression algorithms outperforms state-ofthe-
art compression approaches such as JPEG or HEIC-based
image compression. Unfortunately, most neural-network
based compression methods are executed on GPUs and consume
a high amount of energy during execution. Therefore,
this paper performs an in-depth analysis on the energy
consumption of state-of-the-art neural-network based compression
methods on a GPU and show that the energy consumption
of compression networks can be estimated using
the image size with mean estimation errors of less than 7%.
Finally, using a correlation analysis, we find that the number
of operations per pixel is the main driving force for energy
consumption and deduce that the network layers up to the
second downsampling step are consuming most energy.

Authors with CRIS profile

How to cite

APA:

Herglotz, C., Brand, F., Regensky, A., Rievel, F., & Kaup, A. (2023). Processing Energy Modeling for Neural Network Based Image Compression. In Proceedings of the accepted for IEEE International Conference on Image Processing (ICIP). Kuala Lumpur, MY.

MLA:

Herglotz, Christian, et al. "Processing Energy Modeling for Neural Network Based Image Compression." Proceedings of the accepted for IEEE International Conference on Image Processing (ICIP), Kuala Lumpur 2023.

BibTeX: Download