Metraipolis › archive › dc_1abb9b671fd9

Energy Variation in Training Modern Computer Vision Architectures — arXiv:2610.03772

Source: arXiv
Original: https://arxiv.org/abs/2610.03772
License (as archived): CC0-1.0
Archived: 2026-10-06T05:29:12.857Z
SHA-256 of the archived text: 154c280b425c85ed6eee927bfba2fc436b7976709af67d87a1d1da36b170f065
Stable URL of this page: https://metraipolis.com/documento/dc_1abb9b671fd9

How to cite

Energy Variation in Training Modern Computer Vision Architectures — arXiv:2610.03772 — arXiv, https://arxiv.org/abs/2610.03772 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1abb9b671fd9 (Metraipolis archive dc_1abb9b671fd9, sha256 154c280b425c85ed6eee927bfba2fc436b7976709af67d87a1d1da36b170f065)

BibTeX

@misc{dc1abb9b671fd9,
  title = {Energy Variation in Training Modern Computer Vision Architectures — arXiv:2610.03772},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03772},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1abb9b671fd9; sha256 154c280b425c85ed6eee927bfba2fc436b7976709af67d87a1d1da36b170f065},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03772. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The rapid growth of deep learning has substantially increased the energy consumption associated with model training, making energy efficiency an increasingly relevant design criterion. This study empirically measures the energy variation of training seven modern computer vision architectures, MobileNetV3-Small, MobileNetV3-Large, EfficientNet-B0, EfficientNet-B1, ViT-B/32, ConvNeXt-Tiny, and ViT-B/16 for the ImageNet-1k classification task, using a homogeneous 10,000-image subset (ImageNet-10k) and a uniform 40-epoch baseline configuration executed on two NVIDIA Tesla P100 GPUs at the Bioinformatics and Computational Biology Center of Colombia (BIOS). Energy was recorded directly via NVML and contrasted with the computational complexity of each model. The results show a Pearson correlation of 0.85 between floating-point operations (GFLOPs) and energy consumption in kWh, indicating that computational complexity is a strong but imperfect predictor of energy expenditure: architectures with comparable GFLOPs exhibited consumption differing by up to 3.1x due to differences in the hardware efficiency of their dominant operations. The EfficientNet variants offered the best balance between classification performance (Val Top-5 up to 97.15%) and energy efficiency (0.457-0.611 kWh), while Vision Transformers exhibited the highest relative energy consumption and lower classification performance under the evaluated configuration. These findings guide architecture selection in energy-constrained computing environments.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.PF, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2610.03772 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:25:05.311Z dalla pagina https://arxiv.org/list/cs.PF/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).