detectron-self-train icon indicating copy to clipboard operation
detectron-self-train copied to clipboard

Published 20 hours ago • verified publisher icon AruniRC

Will you open the source code for hard samples mining?

Open SpyderXu opened this issue 5 years ago • 2 comments

Will you open the source code for hard samples mining?

SpyderXu avatar Jun 20 '19 02:06 SpyderXu

Our code was written for running on a cluster over multiple videos in parallel -- it is taking some time to clean this up for a public release. Apologies about this delay.

It is based off the MDNet tracker: https://github.com/HyeonseobNam/MDNet

Thank you for your patience.

AruniRC avatar Jun 22 '19 21:06 AruniRC

Thanks for your awesome works on self-learning. But I have questions about how to use MDNet to mine the hard positives because MDNet is a tracking algorithm for single object tracking and you need to provide bbs for multiple objects in this project. Besides this, I am confused about how to extract the hard bbs from tracking. From my perspective, MDNet is a detection-free tracking approach and would generate many bbs without detectors. Thus, did you use these new bbs by MDNet to filter all bbs (low confidence) by the detection?

Jason-cs18 avatar Aug 12 '19 14:08 Jason-cs18