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.
Source: Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection TasksPaper | Code | Results | Date | Stars |
---|