Some question about the inference about varifocalnet HOT 4 OPEN

Hi, you may change nms=dict(type='soft_nms', iou_threshold=0.5) to nms=dict(type='nms', iou_threshold=0.65) when doing multi-scale testing, and then see the test results. From my experience, soft_nms only brings 0.1 mAP gain when using a huge backbone.

from varifocalnet.

Hi, you may change nms=dict(type='soft_nms', iou_threshold=0.5) to nms=dict(type='nms', iou_threshold=0.65) when doing multi-scale testing, and then see the test results. From my experience, soft_nms only brings 0.1 mAP gain when using a huge backbone.

Thanks for your quick reply. I think that the 'soft nms' or the 'nms' may not cause a big gap but it is possible. The trained model in the first test dataset(A) obtained 58% mAP , but only obtained 52% mAP in the second test dataset(B). And I used the same model to test the second test dataset(B) again, only 41% mAP.

And I would like to know if there are dropped mAP cases randomly in your experiments.

Thanks!

from varifocalnet.

It's a bit weird to see the random drop in performance. I never experienced this in my experiments. But I saw the performance drop when I used soft-nms in multi-scale testing if the iou_threshold was not appropriately set.

from varifocalnet.

It's a bit weird to see the random drop in performance. I never experienced this in my experiments. But I saw the performance drop when I used soft-nms in multi-scale testing if the iou_threshold was not appropriately set.

Thanks for your reply, and thanks for your nice work again. I will conduct some experiments later.

from varifocalnet.