# Unsupervised training of keypoint-agnostic descriptors for flexible retinal image registration

arXiv: https://arxiv.org/abs/2505.02787 · HTML: https://mlsanity.com/paper/2505.02787/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 5 May 2025.

## Builds on (most cited first, 8 of 8)

- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matching](https://mlsanity.com/paper/2207.07932/) (2022)
- [Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited Data](https://mlsanity.com/paper/2307.10698/) (2023)
- [RetinaRegNet: A Zero-Shot Approach for Retinal Image Registration](https://mlsanity.com/paper/2404.16017/) (2024)
- [Progressive Retinal Image Registration via Global and Local Deformable Transformations](https://mlsanity.com/paper/2409.01068/) (2024)
- [ConKeD: Multiview contrastive descriptor learning for keypoint-based retinal image registration](https://mlsanity.com/paper/2401.05901/) (2024)
- [ConKeD++ -- Improving descriptor learning for retinal image registration: A comprehensive study of contrastive losses](https://mlsanity.com/paper/2404.16773/) (2024)

## Abstract (arXiv)

Current color fundus image registration approaches are limited, among other things, by the lack of labeled data, which is even more significant in the medical domain, motivating the use of unsupervised learning. Therefore, in this work, we develop a novel unsupervised descriptor learning method that does not rely on keypoint detection. This enables the resulting descriptor network to be agnostic to the keypoint detector used during the registration inference. To validate this approach, we perform an extensive and comprehensive comparison on the reference public retinal image registration dataset. Additionally, we test our method with multiple keypoint detectors of varied nature, even proposing some novel ones. Our results demonstrate that the proposed approach offers accurate registration, not incurring in any performance loss versus supervised methods. Additionally, it demonstrates accurate performance regardless of the keypoint detector used. Thus, this work represents a notable step towards leveraging unsupervised learning in the medical domain.