MeDAL Retina Dataset

Our primary objective in creating this dataset is to support researchers in the advancement of algorithms for keypoints detection and the pretraining of large models on retinal images using a self-supervised approach. The keypoints in the dataset have been carefully annotated by students from our lab, ensuring meticulous accuracy.

The dataset contains 261 annotated images 1920 images for auxiliary training of the decoder of the descriptors 93209 images for training large models in self-supervised manner