mAP50
A core evaluation metric in object detection that computes the mean of average precision (AP) across all classes at an IoU threshold of 0.5, commonly used to measure whether a detector can locate objects.
Timeline (last 90 days)
mAP50 is a core evaluation metric in object detection, computed as the mean of the average precision of all classes at an IoU threshold of 0.5.
Under controlled RGB-T corruption simulation, PG-FM maintains performance on clean datasets while improving mAP50 under corruption conditions by up to 20.8 points on the FLIR dataset and up to 19.9 points on the KAIST dataset.
All Facts (2)
mAP50 is a core evaluation metric in object detection, computed as the mean of the average precision of all classes at an IoU threshold of 0.5.
50%UnverifiedUnder controlled RGB-T corruption simulation, PG-FM maintains performance on clean datasets while improving mAP50 under corruption conditions by up to 20.8 points on the FLIR dataset and up to 19.9 points on the KAIST dataset.
50%