traing for DHN about deepmot HOT 5 CLOSED

Yes. We don't release yet the code for training DHN.

Please stay tuned.

from deepmot.

Ok, thanks for your kind reply. Another question, when training the DHN model, why we don't use the ground truth of assignment, but the output of original Hungarian algorithm instead.

when construct a binary hard assignment mask to calculate the TPt, we used the ground truth of assignment, isn't it?

Many thanks.

from deepmot.

Hi, actually it is a question about eggs and chickens. We don't know the ground-truth detection/outputs of SOT -to- object assignments. If we know, MOT is not a problem any more. Moreover, the best assignment is always w.r.t a certain criterion. You should define the criterion (appearance similarity, geometry distance, etc.) to calculate the match among them.

However this is only my own understanding.

from deepmot.

Another problem, you say as below in the paper

As described in [6], the input distance values larger than a threshold τd should not lead to an assignment, and are therefore multiplied by a large scaling factor inf before input to the DHN.

but actually you didn't do that in code. And I think it will be set 1.0 instead of inf since the distance has been normalized.

Thanksssss

from deepmot.

Actually we tried both. But it led to similar results. It may due to the fact that the distance tends to 1 and DHN doesn't assign a high probability to it, even without threshold operation.
According to MOT evaluation, you should somehow add the threshold. But it is not a crucial factor for the performance, according to our experiments.

from deepmot.