Bechmark Corrupted Datasets of Fluorescence Images

We have developed three datasets, referred to as ER-C, Mito-C and Nucleus-C, respectively, for benchmarking robustness of DNN models against corruptions and adversarial attacks in semantic segmentation of FM images. Detailed statistics of the datasets are summarized in Table 1. Degraded images in these three datasets are synthesized from raw images with their manually annotated segmentation labels in the ER, Mito, and Nucleus datasets, respectively