# Energy Variation in Training Modern Computer Vision Architectures

arXiv: https://arxiv.org/abs/2610.03772 · HTML: https://mlsanity.com/paper/2610.03772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [An Analysis of Deep Neural Network Models for Practical Applications](https://mlsanity.com/paper/1605.07678/) (2016)
- [InceptionNeXt: When Inception Meets ConvNeXt](https://mlsanity.com/paper/2303.16900/) (2023)
- [Energy Usage Reports: Environmental awareness as part of algorithmic accountability](https://mlsanity.com/paper/1911.08354/) (2019)
- [Training Vision Transformers with Only 2040 Images](https://mlsanity.com/paper/2201.10728/) (2022)
- [Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations](https://mlsanity.com/paper/2403.08151/) (2024)
- [From Computation to Consumption: Exploring the Compute-Energy Link for Training and Testing Neural Networks for SED Systems](https://mlsanity.com/paper/2409.05080/) (2024)
- [Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs](https://mlsanity.com/paper/2404.19331/) (2024)

## Abstract (arXiv)

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.