# OrthKD: Extracting Generalized Clinical Knowledge from Heterogeneous Teachers for Lightweight Deployment

arXiv: https://arxiv.org/abs/2607.25545 · HTML: https://mlsanity.com/paper/2607.25545/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation.
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Placed in

- Knowledge distillation / [Distillation for medical imaging](https://mlsanity.com/distill/distillation-for-medical-imaging/)

## Builds on (most cited first, 10 of 10)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises](https://mlsanity.com/paper/2008.09104/) (2020)
- [Heterogeneous Knowledge Distillation using Information Flow Modeling](https://mlsanity.com/paper/2005.00727/) (2020)
- [Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy](https://mlsanity.com/paper/1710.01711/) (2017)

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

- [If You Hear It, Help Find It: Orthogonal Knowledge Distillation for Open-Vocabulary Audio-Visual Event Localization](https://mlsanity.com/paper/2609.23376/) (2026)

## Abstract (arXiv)

Deploying diabetic retinopathy (DR) screening models in primary care requires edge-efficient systems that remain accurate, safe, and reliable under domain shift. Multi-teacher knowledge distillation (KD) is a natural compression strategy, but existing approaches largely assume that all teachers provide equally trustworthy supervision. In our setting, this assumption fails: a strong CNN teacher (EfficientNet-B3, 0.876 QWK) and a weaker Transformer teacher (Swin-Base, 0.830 QWK) are complementary, yet the Transformer's logits can still mislead the student. We therefore propose OrthKD, a selective-trust distillation framework that transfers full supervision from the strong CNN, uses feature-only distillation from the weak ViT, and enforces orthogonality between teacher-specific student projections to encourage complementary rather than redundant evidence. This design preserves local lesion precision, injects global structural context, and improves robustness to distribution shift. On 132,049 retinal images, a 5.4M-parameter MobileNetV3 student reaches 0.885 QWK on EyePACS and improves zero-shot Messidor-2 performance from 0.507 to 0.728 QWK, while also achieving strong referral AUC and calibration. These results show that selectively distilling heterogeneous teachers can enable practical DR screening on resource-constrained devices.