…There are two common metrics: Detection AUROC and Segmentation (or pixelwise) AUROC Detection (or, classification) methods output single float (anomaly score) per input test image. Segmentation methods output anomaly probability for each pixel. "To assess segmentation performance, we evaluate the relative per-region overlap of the segmentation with the ground truth. We define the true positive rate as the percentage of pixels that were correctly classified as anomalous" 1 Later segmentation metric was improved to balance regions with small and large area, see PRO-AUC
287 PAPERS • 4 BENCHMARKS
Fishyscapes is a public benchmark for uncertainty estimation in a real-world task of semantic segmentation for urban driving.
42 PAPERS • 2 BENCHMARKS
…Uncertainties for Autonomous Driving), consisting of 10,413 realistic synthetic images with diverse adverse weather conditions (night, fog, rain, snow), out-of-distribution objects, and annotations for semantic segmentation
3 PAPERS • NO BENCHMARKS YET
…All unnecessary video segments (e.g., video introductions, news, etc.) that could disturb the learning process were removed.
7 PAPERS • 2 BENCHMARKS
RoadAnomaly21 is a dataset for anomaly segmentation, the task of identify the image regions containing objects that have never been seen during training.
7 PAPERS • NO BENCHMARKS YET
…low number of target pixels (RFI) proportional to the total data volume makes this dataset a useful test for RFI detection schemes in radio astronomy and, more generally, anomaly detection or semantic segmentation
2 PAPERS • 1 BENCHMARK