# Maintaining Performance with Less Data

arXiv: https://arxiv.org/abs/2208.02007 · HTML: https://mlsanity.com/paper/2208.02007/

## 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 (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective](https://mlsanity.com/paper/1811.03402/) (2018)
- [How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?](https://mlsanity.com/paper/1511.06348/) (2015)
- [Efficient-CapsNet: Capsule Network with Self-Attention Routing](https://mlsanity.com/paper/2101.12491/) (2021)
- [An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition](https://mlsanity.com/paper/2008.10400/) (2020)
- [A Data-Centric Approach for Training Deep Neural Networks with Less Data](https://mlsanity.com/paper/2110.03613/) (2021)
- [MetaFormer: A Unified Meta Framework for Fine-Grained Recognition](https://mlsanity.com/paper/2203.02751/) (2022)
- [No Routing Needed Between Capsules](https://mlsanity.com/paper/2001.09136/) (2020)
- [Efficient Classification of Very Large Images with Tiny Objects](https://mlsanity.com/paper/2106.02694/) (2021)
- [Transfer Learning for Sequence Labeling Using Source Model and Target Data](https://mlsanity.com/paper/1902.05309/) (2019)
- [Impact of Training Dataset Size on Neural Answer Selection Models](https://mlsanity.com/paper/1901.10496/) (2019)
- [Data-Efficient Graph Embedding Learning for PCB Component Detection](https://mlsanity.com/paper/1811.06994/) (2018)
- [Towards an Analytical Definition of Sufficient Data](https://mlsanity.com/paper/2202.03238/) (2022)

## 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.