# Targeted transfer learning to improve performance in small medical physics datasets

arXiv: https://arxiv.org/abs/1912.06761 · HTML: https://mlsanity.com/paper/1912.06761/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2019.

## Built on by (most cited first, 11 of 11)

- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [How to Fine-Tune Vision Models with SGD](https://mlsanity.com/paper/2211.09359/) (2022)
- [Comparison of fine-tuning strategies for transfer learning in medical image classification](https://mlsanity.com/paper/2406.10050/) (2024)
- [Addressing materials' microstructure diversity using transfer learning](https://mlsanity.com/paper/2107.13841/) (2021)
- [AI-Driven Real-Time Monitoring of Ground-Nesting Birds: A Case Study on Curlew Detection Using YOLOv10](https://mlsanity.com/paper/2411.15263/) (2024)
- [Differentiable Prompt Learning for Vision Language Models](https://mlsanity.com/paper/2501.00457/) (2024)
- [CoVScreen: Pitfalls and recommendations for screening COVID-19 using Chest X-rays](https://mlsanity.com/paper/2405.07674/) (2024)
- [Transfer or Self-Supervised? Bridging the Performance Gap in Medical Imaging](https://mlsanity.com/paper/2407.05592/) (2024)
- [A Deep Learning-Driven Inhalation Injury Grading Assistant Using Bronchoscopy Images](https://mlsanity.com/paper/2505.08517/) (2025)
- [Bio-inspired fine-tuning for selective transfer learning in image classification](https://mlsanity.com/paper/2601.11235/) (2026)
- [Wearable environmental sensing to forecast how legged systems will interact with upcoming terrain](https://mlsanity.com/paper/2602.09209/) (2026)

## Abstract (arXiv)

The growing use of Machine Learning has produced significant advances in many fields. For image-based tasks, however, the use of deep learning remains challenging in small datasets. In this article, we review, evaluate and compare the current state-of-the-art techniques in training neural networks to elucidate which techniques work best for small datasets. We further propose a path forward for the improvement of model accuracy in medical imaging applications. We observed best results from one cycle training, discriminative learning rates with gradual freezing and parameter modification after transfer learning. We also established that when datasets are small, transfer learning plays an important role beyond parameter initialization by reusing previously learned features. Surprisingly we observed that there is little advantage in using pre-trained networks in images from another part of the body compared to Imagenet. On the contrary, if images from the same part of the body are available then transfer learning can produce a significant improvement in performance with as little as 50 images in the training data.