search

hfslyc / AdvSemiSeg

Adversarial Learning for Semi-supervised Semantic Segmentation, BMVC 2018
504 stars 129 forks source link

confidence map #24

Closed LeiyuanMa closed 5 years ago

LeiyuanMa commented 6 years ago

Excuse me, There are one more questions...hope it not bothing you too much... "The output of D is a probability map with values ranges from 0-1. When the input is unlabeled data, we use the D output map as the indicator for semi-supervised learning."

D_out = interp(model_D(F.softmax(pred))) D_out_sigmoid = F.sigmoid(D_out).data.cpu().numpy().squeeze(axis=1)

following is used to draw the confindence map in your papar Figure3

    for i in range(args.batch_size):
           plt.imshow(D_out_sigmoid[i], cmap='jet')
           plt.show()

Can I interpret the D_out_sigmoid is the confidence map you mentioned? I use VOC_20000.pth and VOC_20000_D.pth(when use these two model the evaluatation mIOU is 0.709) as the parameters for RESTORE_FROM and RESTORE_FROM_D,and tried to get the figure of confidence map,but it looks not matching so well,it looks weird ,can you explain how you get the confidence map in your paper?

hfslyc commented 6 years ago

the code looks fine to me. What do you mean by "not matching so well"?

LeiyuanMa commented 6 years ago

plt.imshow(D_out_sigmoid[i], cmap='jet') Does this image should looks close to the ground truth?

LeiyuanMa commented 6 years ago

and Is it the right way to draw confidence map?

hfslyc commented 6 years ago

the map is not related to ground truth. It's the discriminator score on how close it is to the ground truth.

On Fri, Nov 2, 2018 at 10:58 PM Degage notifications@github.com wrote:

and Is it the right way to draw confidence map?

— You are receiving this because you commented.

Reply to this email directly, view it on GitHub https://github.com/hfslyc/AdvSemiSeg/issues/24#issuecomment-435563356, or mute the thread https://github.com/notifications/unsubscribe-auth/AKhYAcdYsa3mqGga16lUPO0vlDTV5tOvks5urTBogaJpZM4YMpKD .