Closed bhack closed 7 years ago
Thanks a lot for your interest in our work! We will publish the code upon acceptance of the paper.
Where was submitted?
We have submitted it to a journal and we are waiting for their reviews.
I cannot see in the paper if you have experimented the fine-tuning of the instance segmentation mask network using the GT of the 1st frame.
In the paper we use the instance segmentation network out of the box without any fine-tuning.
Yes I've seen.. but have you experimented the fine-tuning? Degraded?
In DAVIS 2016, instances from different classes are mixed in the same mask so it would be difficult to use the 1st frame gt mask to fine-tune a specific class of the instance segmentation network.
But Davis 2017 could not have this problem
It could be, but we haven't done any experiments in that direction.
So, next extension :)
Do you plan to release the new OSVOS-S with instance segmentation?