Giters

valeoai / LOST

Pytorch implementation of LOST unsupervised object discovery method

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Multi-object discovery

rgbd-zml opened this issue · comments

commented

HI, I have a confusion about the interesting work.
How to perform multi-target discovery in the figure 1 (middle) of your paper？
Any advice is greatly appreciated.

commented

Hi @rgbd-zml,
Thank you for your interest.
Our method LOST discovers one object per image. However, we subsequently train a detector in a fully-supervised fashion using the detections of LOST as pseudo ground-truth. Doing so we obtain a detector that outputs several predictions per image, which was used to obtain the middle figure in Figure 1 of our paper. I hope this helps!