mlsanityData to 7 Oct 2026

NoFADE: Analyzing Diminishing Returns on CO2 Investment

arXiv 2111.14059 ↗First posted 28 Nov 2021cs.CV cs.CY cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Climate change continues to be a pressing issue that currently affects society at-large. It is important that we as a society, including the Computer Vision (CV) community take steps to limit our impact on the environment. In this paper, we (a) analyze the effect of diminishing returns on CV methods, and (b) propose a textit``NoFADE'': a novel entropy-based metric to quantify model--dataset--complexity relationships. We show that some CV tasks are reaching saturation, while others are almost fully saturated. In this light, NoFADE allows the CV community to compare models and datasets on a similar basis, establishing an agnostic platform.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 55 references that are in the map. First posted on arXiv 28 Nov 2021.

Builds on

38 of 55 references.

References · 38

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  10. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  11. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  12. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
26 more
  1. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  2. 2021Going deeper with Image Transformerscited by 759
  3. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  4. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  5. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  6. 2019Selective Kernel Networkscited by 401
  7. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  8. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  9. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  10. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 140
  11. 2018ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentationcited by 133
  12. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  13. 2020TResNet: High Performance GPU-Dedicated Architecturecited by 119
  14. 2019Seamless Scene Segmentationcited by 112
  15. 2019Knowledge Adaptation for Efficient Semantic Segmentationcited by 105
  16. 2019DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationcited by 100
  17. 2019DetNAS: Backbone Search for Object Detectioncited by 80
  18. 2019ThunderNet: Towards Real-time Generic Object Detectioncited by 42
  19. 2019LIP: Local Importance-based Poolingcited by 30
  20. 2020Measures of Complexity for Large Scale Image Datasetscited by 14
  21. 2019Light-Weight RetinaNet for Object Detectioncited by 11
  22. 2018ShuffleSeg: Real-time Semantic Segmentation Networkcited by 9
  23. 2020Funnel Activation for Visual Recognitioncited by 9
  24. 2020MicroNet: Towards Image Recognition with Extremely Low FLOPscited by 9
  25. 2021Reconsidering CO2 emissions from Computer Visioncited by 9
  26. 2018Efficient Semantic Segmentation using Gradual Groupingcited by 1

Built on by

Not cited yet.