Optimization problem: missing m_hat parameters about utae-paps HOT 15 CLOSED

Hi @alexanderDuenas ,
I pushed the implementation for the generation of the ground truth heatmaps, where you will also see how the zones tensor is obtained.
I pushed it in the dataset repository.

from utae-paps.

Hi @GustavoMourao !
So Eq. 6 shows how to obtain the centerness ground truth, and in this formula $\hat{i}{p}$ and $\hat{j}{p}$ denote the ground truth position of a given parcel $p$. Hence, a parcel in a given patch will result in a Gaussian kernel centred on $ (\hat{i}{p} , \hat{j}{p}) $ in the centerness ground truth.
Does that answer your question ?

from utae-paps.

I've got it!

However, have you used the original CenterMask implementation in order to get the heatmap, and the centerness ground truth, as well?

Besides of that, I haven't fully understood how you obtained the Zones? Was that extracted from centerness ground truth?

Thank you very much!

from utae-paps.

Great!
We didn't use the CenterMask implementation we computed the centerness ground truth as described in Eq.6.
I think that in CenterMask the kernels are homoscedastic whereas we use heteroscedastic kernels that depend on the parcel's two dimensions.

For the Zones see this issue : #6

from utae-paps.

I see.

However, how have you calculated the ground truth heatmap, used as target that feed the loss function? In this case, the target heatmap used into Class PaPsLoss?

from utae-paps.

that's what I mean (centerness ground truth = ground truth heatmap), so Eq. 6

from utae-paps.

Haven't you implemented Equation 6 in Class PaPs? If so, those results above represents the target heatmap and the calculated value from forwar method (class PaPs).

If not, have you implemented Eq.6?

Cheers

from utae-paps.

The left figure is the result of our implementation of Eq. 6.
But the implementation is not contained in PaPs, the ground truth heatmap was computed once and for all and stored in the annotations of the dataset.

from utae-paps.

Great, I see.

So, could you share the methodology used to obtain the ground truth heatmap? It seems that isn't just the argmax of each parcel..

Thanks a lot!

from utae-paps.

Well the ground truth heatmap is obtained with Eq. 6 ! ^^

from utae-paps.

Maybe you are thinking of the mapping pixel->parcel (the "zones" tensor) ?

from utae-paps.

I see.

But look, do you use the Eq. 6 as parameter of your loss function, right (PaPsLoss)? And, considering this, do you use the same estimation (Eq.6) during the inference?

from utae-paps.

This is the target signal for PaPsLoss, and specifically for the centerness regression head.
It is used as target signal during training.
You don't need this at inference time.

from utae-paps.

I've got.

I think that I misunderstanding the optimization loss func. ;)

Thank you for the support

from utae-paps.

Hi Dears!

Is it possible to upload or share the code implementation for the eq 6 for generating the ground-truth heatmaps?

from utae-paps.