Skip to content
InfoResearchPreprint

Quantum-inspired orthogonal adapters for certifiably robust medical image classification

Published
Record updated
View JSON

Summary

This paper proposes fine-tuning certified medical image classifiers with quantum-inspired orthogonal butterfly layers, which keep the Lipschitz bounds of pretrained networks while using only O(n log n) trainable parameters. On MNIST and MedMNIST the approach improves certified robustness over conventional alternatives, and on trichoscopic alopecia images it reaches roughly twice the certified accuracy of conventional fine-tuning and LoRA at comparable classification accuracy.