Open aL3x-O-o-Hung opened 2 months ago
Can you show some examples?
The scribbles were generated using the code in scribbleprompt/scribbles.py
during training.
Hi!
Thanks for the reply. Please find these examples attached.
Those scribbles look quite thick, relative to the size of the images. The random deformations in our scribble generation code vary the scribble thickness a bit but the training scribbles are rarely as wide and as sharp as these examples. I suspect the predictions will be much better with thinner scribbles and/or lightly blurring the scribble mask.
So I generated some fake scribbles on our dataset using the ground truth labels but the pretrained model cannot predict anything meaningful while using the generate clicks and bounding boxes are fine. I am wondering how the scribbles are generated and how the generated scribbles can shift the input distribution so much that it completely confuse the network.