clarification on norm loss calculation; possible bug? about super-bpd HOT 6 CLOSED

We define gt flux at each pixel as a two-dimensional unit vector pointing from its nearest boundary to the pixel. So gt flux around medial points have nearly opposite directions. It is difficult for neural networks to learn such sharp changes, and the network is more inclined to get a smooth transition (like from -1 to 1, network tend to output -1 -0.5 0 0.5 1).

For the norm loss, gt flux is a two-dimensional unit vector field, pred flux does not to be normalized.
For the angle loss, normalize pred flux inside or outside of torch.acos is the same.

from super-bpd.

Emmm, I am sorry for the confusion of norm gt (It is wrong, norm gt should be 1 at each pixel. Actually, it is a distance transform map). The calculation of gt flux can be seen in sec 3.1 of origin paper, returned gt_flux of datasets.py is not normalized by corresponding distance because the visualization of norm gt will be collapse.

from super-bpd.

thanks for the fast response @JianqiangWan !

however do you understand my concern with the pred_norm collapsing at unexpected places? perhaps I'm misunderstanding pred_norm?

from super-bpd.

i am also then confused that

gt_flux is normalized (because it was not in datasets.py) for the norm loss

but pred_flux is normalized for the angle loss and not the norm loss

from super-bpd.

thanks for the thorough response

let me make sure I understand:

1. gt flux transitions directionality upon hitting the medial points. we can see this difficulty in learning sharp transitions in the difference between angle_gt and angle_pred: the transition from media to the boundary in angle_pred shows a gradient (like you mention -1 -0.5 0 0.5 1). your explanation makes sense to me for the angles and is born out by the actual behavior of the network.
2. however, my primary concern is specifically with the norm component. my understanding is that these are direction agnostic, as seen in norm_gt where we see:

boundary ---- medial point ---- boundary
     0 1 2 3 4 5 6 7 6 5 4 3 2 1 0

however, we do not see that this is the case for norm_pred. the network seems to always predict:

boundary ---- medial point ---- boundary
     0 1 1 1 1 1 1 0 1 1 1 1 1 1 0

from super-bpd.

We need two channels (x, y) to express a flux field, gt flux around medial points can be roughly expressed as (x1, y1) and (-x1, -y1) since they have opposite direction.

From -x1 to x1 or -y1 to y1, network hardly gets the sharp transition, tending to get smooth transition.
norm = sqrt( x**2 + y**2), so pred norm between medial points (x to -x) or boundary points (-x to x) is very small, but the angle is still correct (we only use angle information for image segmentation).
Again, norm gt at each pixel is 1, 'norm gt' in the picture is a distance transform map before normalization.

from super-bpd.