You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the initial stage of training, the scores of task alignment learning metric are so small, so that theirs value are almost zero, because of low ious and classification scores. As my point of view, using the ATSS is aim to select positive samples closing to gt center points in order to accelerate the model convergence in the early training?
The text was updated successfully, but these errors were encountered:
Yes. Using ATSS aims to select the relatively good anchors (which are close to gt center points in most cases) as an initialization for TOOD. You also can use other sample assigners to initialize the detector.
In the initial stage of training, the scores of task alignment learning metric are so small, so that theirs value are almost zero, because of low ious and classification scores. As my point of view, using the ATSS is aim to select positive samples closing to gt center points in order to accelerate the model convergence in the early training?
The text was updated successfully, but these errors were encountered: