0
$\begingroup$

I am wondering if it is required or not that the masks used for binary instance segmentation are complete.

For instance, I want to find the buildings in aerial imagery. If my masks cover, let say between 25% and 75% of the training image buildings, can these samples be used for training the model? Does the masks should cover 100% of the buildings in the samples?

I know it would be better to mask all buildings, but if the mask is not complete, can it be used for training or not?

I am using a deeplabv3 model.

Here an example of what I mean enter image description here

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

You can train a model with that dataset, but it will perform worse compared to a higher fidelity dataset. Training on images with unannotated buildings is essentially instructing the model to stochastically ignore buildings, which is confusing.

Improve this answer
$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .