# ConKeD++ -- Improving descriptor learning for retinal image registration: A comprehensive study of contrastive losses Source: [ConKeD++ -- Improving descriptor learning for retinal image registration: A comprehensive study of contrastive losses]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:33:04.779Z Authors: David Rivas-Villar, \\'Alvaro S. Hervella, Jos\\'e Rouco, Jorge Novo Published: 2024-04-25T17:24:35.000Z ## Abstract Self-supervised contrastive learning has emerged as one of the most successful deep learning paradigms. In this regard, it has seen extensive use in image registration and, more recently, in the particular field of medical image registration. In this work, we propose to test and extend and improve a state-of-the-art framework for color fundus image registration, ConKeD. Using the ConKeD framework we test multiple loss functions, adapting them to the framework and the application domain. Furthermore, we evaluate our models using the standarized benchmark dataset FIRE as well as several datasets that have never been used before for color fundus registration, for which we are releasing the pairing data as well as a standardized evaluation approach. Our work demonstrates state-of-the-art performance across all datasets and metrics demonstrating several advantages over current SOTA color fundus registration methods ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Retinal Image Registration on FIRE (overall)](): Retinal Image Registration; FIRE (overall); A Score: 76.6. ## Original sources and implementation [Original paper]() [PDF]()