I’m working on an object detection cnn, and having some issues with non max suppression. When I have a small box inside a large box, NMS is not rejecting the smaller, incorrect box, because its IOU is small (large union, small intersection). How is this scenario typically dealt with? When using out of the box pretrained models for object detection I don’t seem to get boxes completely inside other boxes. Example here: green is ground truth, blue is prediction. The center box has a tiny blue box inside that’s not getting rejected by NMS
IOU makes sense for determining accuracy against ground truth, but for non max suppression have you tried intersection over minimum size?
$\begingroup$ Possibly but this isn’t standard practice. Standard COCO object detectors like SSD and FasterRCNN don’t seem to have such issues $\endgroup$– A TyshkaJun 10, 2021 at 1:55