R2CNN_Faster-RCNN_Tensorflow
R2CNN_Faster-RCNN_Tensorflow copied to clipboard
How to add negative data ?
The reason i am asking this question is because of the algorithm implemented here works differently for negative data.
For example, Faster R-CNN considers as negative boxes those which have IoU under a certain threshold (0.3 by default, I think). And then it takes as many negative examples as positive ones.
So basically, if you have your object B in images with A as well, and it is not labeled, it is some chance that it will be considered as a negative.
Please correct me if i am wrong ! Can you tell me how can i add negative data without tagging ?
This article may give you some inspiration. https://arxiv.org/pdf/1806.06986.pdf
Links only partially answers the question.
If i have some images that do not have any objects and i would like to add it as negative ..how do i go about it ?