Lune

ICML2025Top-tier venue

The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference

Zeyu Yang, Wesley Armour

Abstract

Deep learning has achieved significant success but poses increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of understanding of their energy efficiency during inference. In this study, we conduct a comprehensive analysis of the inference energy consumption of 1,200 ImageNet classification models-the largest evaluation of its kind to date. Our findings reveal a steep decline in accuracy gains relative to the increase in energy usage, highlighting sustainability concerns in the pursuit of marginal improvements. We identify key factors contributing to energy consumption and demonstrate methods to improve energy efficiency. To promote more sustainable AI practices, we introduce an energy efficiency scoring system and develop an interactive web application that allows users to compare models based on accuracy and energy consumption. By providing extensive empirical data and practical tools, we aim to facilitate informed decision-making and encourage collaborative efforts in the development of energyefficient AI technologies.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization cites Natural Adversarial Examples
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution GeneralizationDan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath et al.ICCV 2021 · 2,294 citations
  2. PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph CompilationJason Ansel, Edward Z. Yang, Horace He, Natalia Gimelshein et al.ASPLOS 2024 · 693 citations
  3. Accurate and Convenient Energy Measurements for GPUs: A Detailed Study of NVIDIA GPU's Built-In Power SensorZeyu Yang, Karel Adámek, Wesley ArmourSC 2024 · 38 citations
  4. Natural Adversarial ExamplesDan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt et al.CVPR 2021

Related papers

  1. Energy Considerations of Large Language Model Inference and Efficiency OptimizationsJared Fernandez, Clara Na, Vashisth Tiwari, Yonatan Bisk et al.ACL 2025
  2. Green AI: Do Deep Learning Frameworks Have Different Costs?Stefanos Georgiou, Maria Kechagia, Tushar Sharma, Federica Sarro et al.ICSE 2022 · 90 citations
  3. TokenPowerBench: Benchmarking the Power Consumption of LLM InferenceChenxu Niu, Wei Zhang, Jie Li, Yongjian Zhao et al.AAAI 2026 · 12 citations
  4. EA-HAS-Bench: Energy-aware Hyperparameter and Architecture Search BenchmarkShuguang Dou, Xinyang Jiang, Cairong Zhao, Dongsheng LiICLR 2023
  5. Tensor-Aware Energy AccountingTimur Babakol, Yu David LiuICSE 2024 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines