Questions tagged [mask-rcnn]
For questions about the mask R-CNN model, proposed in the paper "Mask R-CNN" (2018) by Kaiming He et al.
13
questions
4
votes
1
answer
1k
views
How does Mask R-CNN automatically output a different number of objects on the image?
Recently, I was reading Pytorch's official tutorial about Mask R-CNN.
When I run the code on colab, it turned out that it automatically outputs a different number of channels during prediction. If the ...
- 882
3
votes
1
answer
943
views
Is Mask R-CNN suited to solve a multi-class classification problem where the classes are related?
I want to create a model to solve a multi-class classification problem.
Here are more details about my problem.
Every picture contains only one object
The background is very simple
All objects ...
- 31
2
votes
2
answers
218
views
How to instruct Mask RCNN to identify objects too close to each other?
I have been trying to train a Mask RCNN model to identify individual poker chips in a stack. No matter what property I change, the end results look like the following image. I was guessing the issue ...
- 29
2
votes
0
answers
603
views
Getting bounding box/boundaries from segmentations in UNet Nuclei Segmentation
From my understanding, in a tissue where nuclei are present and need to be detected, we need to predict bounding boxes (either rectangular/circular or in the shape of the nucleus, i.e. as in instance ...
- 159
2
votes
0
answers
2k
views
How much should we augment our training data?
I am wondering how much I should extend my training set with data augmentation. Is there somewhere a pre-defined number I can go with?
Suppose I have 10000 images, can I go as far as 10x or 20x times, ...
- 21
1
vote
1
answer
54
views
possible to combine multiple labeled objects as one object?
So I have labeled the entire skeletal muscles in detail. For example instead of just labeling shoulders I have labeled:
Rear Delt
Middle Delt
Front Delt
but now you want all of the delts to be ...
- 11
1
vote
0
answers
69
views
Ways to train a neural network continuosly as new data is added [duplicate]
There is a project I'm currently working on that requires object detection with continuous training. The idea is to train a model beforehand with a standard dataset. When I get new images I want to &...
1
vote
1
answer
408
views
Mask R-CNN: How are the computed masks projected back to the input image?
The computed masks by Mask R-CNN are of fixed size $m \times m$ each. How are they projected back to the image?
- 21
1
vote
0
answers
305
views
Mask R-CNN: how is the inference done?
According to the Mask R-CNN paper and the picture below (taken from the paper), the mask branch is computed in parallel with the bbox classification and regression branches.
However in the paper they ...
- 21
1
vote
0
answers
39
views
Can I use a Mask R-CNN to detect a skin texture?
I'm trying to implement a solution in python to detect skin in an image.
I'm evaluating the Mask R-CNN model to create a mask on the skin (not on clothes). The problem is that every solution I have ...
- 11
0
votes
1
answer
37
views
Why instance segmentation architectures using reconstruction masks but not regression?
I'm wondering why many model architectures use binary mask reconstruction for segmentational CNNs, and not regression of mask polygon coordinates? Many object detectors use regression to find ...
- 103
0
votes
0
answers
30
views
How can you add additional features/attributes while doing instance segmentation?
I want to do an instance segmentation of objects in images.
Usually I would stick to something like an Mask R CNN and let it run. However additionally to the image itself and the pre-labeled images, I ...
- 101
0
votes
0
answers
107
views
Improving Mask RCNN by arbitrary scaling head input
Currently, I am looking at how Mask R-CNN works. It has a backbone, RPN, heads, etc. The backbone is used for creating the feature maps, which are then passed to the RPN to create proposals. Those ...
- 101