Partially labelled semantic segmentation
3 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Hi, I'm trying to use partially labelled images as a groud truth for the semantic segmentation training(there are lots of ambiguous regions in my images, so i am hoping to train only with the apparent regions; by inputting the class weight 0(techinically it was 10^-20 as I cannot input zero) to the unlabeled class in pixel classification layer)
And I found that the mini-batch accuracy is fluctuates around 35-40% and never converges.
Are there any ways i could fix this problem?
Is it related to excessive non-labeled regions?
I would appreciate any of your advice concerning this problem.
0 commentaires
Réponse acceptée
Raunak Gupta
le 3 Oct 2020
Hi,
Assigning zero class weight to unlabeled pixel will help in removing them from loss calculation during training however when the accuracy metrics are calculated after training, it will include all the pixels and thus giving random categories to unlabeled pixel (I am assuming there is more than 1 class in labeled pixels).
Instead I will recommend assigning a background category to unlabeled pixel and keeping the class weight same as labeled pixel so that network can assign proper categories to all the pixels (background pixel can also be trained). This way network will be more robust for all parts of the image. So, adding one more class named background to the previous classes may help you converge to a higher accuracy.
7 commentaires
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Image Data Workflows dans Help Center et File Exchange
Produits
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!