Closed ring-zl closed 8 months ago
low confidence threshold aims to improve the recall for temporal action detection, this trick is common in object detection and temporal action detection.
thank you. What surprises me is that this rather extreme approach leads to a significant increase in the number of False Positives , but ultimately results in a noticeable improvement in the mAP metric。
To clarify, we are using soft NMS, which does not impose a threshold and keeps all detection output. If you are looking at _iouthreshold, this is not a hard threshold for soft NMS.
"Why is the confidence threshold for NMS set quite low in the experiment, resulting in a significantly high number of prediction outputs? Is this practically feasible? Moreover, why does appropriately increasing the NMS confidence threshold (for instance, to 0.1 or 0.3) lead to a noticeable decrease in mAP?"