mlsanityData to 14 Oct 2026

Reconsidering CO2 emissions from Computer Vision

arXiv 2104.08702 ↗First posted 18 Apr 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Climate change is a pressing issue that is currently affecting and will affect every part of our lives. It's becoming incredibly vital we, as a society, address the climate crisis as a universal effort, including those in the Computer Vision (CV) community. In this work, we analyze the total cost of CO2 emissions by breaking it into (1) the architecture creation cost and (2) the life-time evaluation cost. We show that over time, these costs are non-negligible and are having a direct impact on our future. Importantly, we conduct an ethical analysis of how the CV-community is unintentionally overlooking its own ethical AI principles by emitting this level of CO2. To address these concerns, we propose adding "enforcement" as a pillar of ethical AI and provide some recommendations for how architecture designers and broader CV community can curb the climate crisis.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 43 of its 61 references that are in the map. First posted on arXiv 18 Apr 2021.

Builds on

43 of 61 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Going Deeper with Convolutionscited by 4,241
  4. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  5. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  6. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  7. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  8. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  9. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  10. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  11. 2018SNAS: Stochastic Neural Architecture Searchcited by 289
  12. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
31 more
  1. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 202
  2. 2017Hierarchical Representations for Efficient Architecture Searchcited by 191
  3. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 188
  4. 2018Neural Architecture Optimizationcited by 167
  5. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  6. 2018Graph HyperNetworks for Neural Architecture Searchcited by 132
  7. 2019Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Searchcited by 131
  8. 2019Blockwisely Supervised Neural Architecture Search with Knowledge Distillationcited by 81
  9. 2019Network Pruning via Transformable Architecture Searchcited by 80
  10. 2019One-Shot Neural Architecture Search via Self-Evaluated Template Networkcited by 69
  11. 2019SGAS: Sequential Greedy Architecture Searchcited by 69
  12. 2020AttentiveNAS: Improving Neural Architecture Search via Attentive Samplingcited by 66
  13. 2020Neural Architecture Transfercited by 60
  14. 2020MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulationcited by 57
  15. 2019Densely Connected Search Space for More Flexible Neural Architecture Searchcited by 52
  16. 2018Path-Level Network Transformation for Efficient Architecture Searchcited by 44
  17. 2019AtomNAS: Fine-Grained End-to-End Neural Architecture Searchcited by 40
  18. 2020Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Searchcited by 38
  19. 2017N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learningcited by 33
  20. 2020TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Searchcited by 21
  21. 2019sharpDARTS: Faster and More Accurate Differentiable Architecture Searchcited by 19
  22. 2019Multinomial Distribution Learning for Effective Neural Architecture Searchcited by 17
  23. 2015Deep Image: Scaling up Image Recognitioncited by 16
  24. 2020Noisy Differentiable Architecture Searchcited by 16
  25. 2020Anti-Bandit Neural Architecture Search for Model Defensecited by 16
  26. 2019Efficient Forward Architecture Searchcited by 14
  27. 2020DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Searchcited by 14
  28. 2020MUXConv: Information Multiplexing in Convolutional Neural Networkscited by 12
  29. 2018Teacher Guided Architecture Searchcited by 10
  30. 2019Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?cited by 10
  31. 2019SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Searchcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 2; 2024: 2; 2025: 2.

9 papers.

  1. 2024MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AIcited by 16
  2. 2023To Spike or Not To Spike: A Digital Hardware Perspective on Deep Learning Accelerationcited by 10
  3. 2023End-to-End Supervised Multilabel Contrastive Learningcited by 8
  4. 2025Quantum-enhanced Computer Vision: Going Beyond Classical Algorithmscited by 5
  5. 2022Exploiting Explainable Metrics for Augmented SGDcited by 2
  6. 2024Estimating Environmental Cost Throughout Model's Adaptive Life Cyclecited by 2
  7. 2021P4AI: Approaching AI Ethics through Principlismcited by 1
  8. 2025CarboFormer: A Lightweight Semantic Segmentation Architecture for Efficient Carbon Dioxide Detection Using Optical Gas Imagingcited by 1
  9. 2021NoFADE: Analyzing Diminishing Returns on CO2 Investmentcited by 0