Questions tagged [semantic-segmentation]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
1answer
22 views

What is Deep supervision?

I'm interested in segmentation models for medical imaging purposes. When I looked at the state of the art, I fell on a paper on a new architecture, Unet++: UNet++: A Nested U-Net Architecture for ...
1
vote
0answers
25 views

Tool for annotation of images for semantic segmentation

I have been searching around for a software tool, that I can use for annotating images. More specifically I want to do annotation to be used for semantic segmentation, meaning I want to create masks. ...
1
vote
0answers
19 views

Image segmentation with large class imbalance leads to zero precision/recall

I have a binary semantic image classification problem where only very small parts of the images are positive, most of it is negative. In the training data I have a positive rate of around 0.023, which ...
0
votes
2answers
42 views

How to extract contents by topic from a document?

I am trying to extract information from resumes. I tried the pdfminer for the text extraction. But I need to extract the contents from a resume with respect to its title. For example: I will be giving ...
0
votes
0answers
23 views

Multi-task Learning and Multi-task Loss

I'm working with Mask R-CNN and want to understand the relationship between the produced losses Lmask, Lclass, Lbox which are eventually making up the muli-loss output and generally, multi-task ...
0
votes
1answer
24 views

Semantic networks: word2vec?

I have some doubts on how to represent the relationships between words in texts. Let’s suppose I have two sentences like these: ...
0
votes
1answer
37 views

For semantic sementation, why am I getting better loss values with binary cross entropy than dice coef?

I'm learning all related to data science and how to train U-Net to do semantic segmentation. I have a U-NET with this loss function: ...
1
vote
0answers
13 views

How to approach coarse-grained semantic segmentation?

I’m looking at doing something like semantic segmentation of images but where I only have pretty coarse-grained labels - roughly, for each 32x32 patch, I know if the answer should be “yes”, “no” or “...