{"url":"/dataset/retina-benchmark","name":"Retina Benchmark","full_name":null,"description_markdown":"The **Retina Benchmark** is a set of real-world tasks that accurately reflect such complexities and are designed to assess the reliability of predictive models in safety-critical scenarios. Specifically, two publicly available datasets of high-resolution human retina images exhibiting varying degrees of diabetic retinopathy, a medical condition that can lead to blindness, are used to design a suite of automated diagnosis tasks that require reliable predictive uncertainty quantification.\r\n\r\nSource: [Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks](https://arxiv.org/pdf/2211.12717v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.12717v1.pdf](https://arxiv.org/pdf/2211.12717v1.pdf)","description_withheld":null,"homepage":"https://github.com/google/uncertainty-baselines/tree/main/baselines/diabetic_retinopathy_detection","introduced_date":"2022-11-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/benchmarking-bayesian-deep-learning-on","title":"Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks","first_author":"Neil Band","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Diabetic Retinopathy Detection","url":"/task/diabetic-retinopathy-detection","datasets_with_task":"/datasets/task/diabetic-retinopathy-detection"}],"languages":[],"variants":["Retina Benchmark"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}