mlsanityData to 14 Oct 2026

Maintaining Performance with Less Data

arXiv 2208.02007 ↗First posted 3 Aug 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a novel method for training a neural network for image classification to reduce input data dynamically, in order to reduce the costs of training a neural network model. As Deep Learning tasks become more popular, their computational complexity increases, leading to more intricate algorithms and models which have longer runtimes and require more input data. The result is a greater cost on time, hardware, and environmental resources. By using data reduction techniques, we reduce the amount of work performed, and therefore the environmental impact of AI techniques, and with dynamic data reduction we show that accuracy may be maintained while reducing runtime by up to 50%, and reducing carbon emission proportionally.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 3 Aug 2022.

Builds on

20 of 34 references.

References · 20

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  3. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  4. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  6. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  7. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  8. 2020The Computational Limits of Deep Learningcited by 193
  9. 2018A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspectivecited by 112
  10. 2015How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?cited by 45
  11. 2021Efficient-CapsNet: Capsule Network with Self-Attention Routingcited by 41
  12. 2020An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognitioncited by 30
8 more
  1. 2021A Data-Centric Approach for Training Deep Neural Networks with Less Datacited by 28
  2. 2022MetaFormer: A Unified Meta Framework for Fine-Grained Recognitioncited by 28
  3. 2020No Routing Needed Between Capsulescited by 27
  4. 2021Efficient Classification of Very Large Images with Tiny Objectscited by 17
  5. 2019Transfer Learning for Sequence Labeling Using Source Model and Target Datacited by 8
  6. 2019Impact of Training Dataset Size on Neural Answer Selection Modelscited by 7
  7. 2018Data-Efficient Graph Embedding Learning for PCB Component Detectioncited by 4
  8. 2022Towards an Analytical Definition of Sufficient Datacited by 3

Built on by

Not cited yet.