# Domain Specific, Semi-Supervised Transfer Learning for Medical Imaging

arXiv: https://arxiv.org/abs/2005.11746 · HTML: https://mlsanity.com/paper/2005.11746/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2020.

## Built on by (most cited first, 1 of 1)

- [Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment](https://mlsanity.com/paper/2608.16804/) (2026)

## Abstract (arXiv)

Limited availability of annotated medical imaging data poses a challenge for deep learning algorithms. Although transfer learning minimizes this hurdle in general, knowledge transfer across disparate domains is shown to be less effective. On the other hand, smaller architectures were found to be more compelling in learning better features. Consequently, we propose a lightweight architecture that uses mixed asymmetric kernels (MAKNet) to reduce the number of parameters significantly. Additionally, we train the proposed architecture using semi-supervised learning to provide pseudo-labels for a large medical dataset to assist with transfer learning. The proposed MAKNet provides better classification performance with 60 - 70% less parameters than popular architectures. Experimental results also highlight the importance of domain-specific knowledge for effective transfer learning.