MSCOCO mAP about pva-faster-rcnn HOT 5 OPEN

Here are my intermediate results. I will update it again when I complete 500k training iteration.

from pva-faster-rcnn.

Since our target was to develop a detector for few selected objects,
we haven't evaluated our models on the MS COCO (80 class) dataset.

from pva-faster-rcnn.

Here is the updated and final results for your reference. Note that I do not try the best parameters here and if we do some fine adjustment, the results could get better.

from pva-faster-rcnn.

more updated here! Note that the train data i used for pvanet-full is less than that of other methods in comparsion. Maybe I need to redo the experiments later.
(there is typo error: plateau windows should be 50k,50k,50k)

from pva-faster-rcnn.

how about the resolution of the image's short edge for coco test data?

from pva-faster-rcnn.