# Improving image classifiers for small datasets by learning rate adaptations

arXiv: https://arxiv.org/abs/1903.10726 · HTML: https://mlsanity.com/paper/1903.10726/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2019.

## Built on by (most cited first, 2 of 2)

- [Predicting O-GlcNAcylation Sites in Mammalian Proteins with Transformers and RNNs Trained with a New Loss Function](https://mlsanity.com/paper/2402.17131/) (2024)
- [A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information](https://mlsanity.com/paper/2212.04314/) (2022)

## Abstract (arXiv)

Our paper introduces an efficient combination of established techniques to improve classifier performance, in terms of accuracy and training time. We achieve two-fold to ten-fold speedup in nearing state of the art accuracy, over different model architectures, by dynamically tuning the learning rate. We find it especially beneficial in the case of a small dataset, where reliability of machine reasoning is lower. We validate our approach by comparing our method versus vanilla training on CIFAR-10. We also demonstrate its practical viability by implementing on an unbalanced corpus of diagnostic images.