Questions tagged [semantic-segmentation]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
8 views

How to use UPSNet or Mask-RCNN? How to format image data for panoptic segmentation?

I want to use UPSNet (github repo) (paper) to train a model to perform panoptic segmentation on my own dataset. I would also consider using a model based on Mask-RCNN to simply perform instance ...
  • 1
0 votes
1 answer
22 views

How does mixing and matching encoders and decoders work in image segmentation?

I had a conceptual questions regarding architectures. I am using this git hub repository that allows one to quickly put together a segmentation pipeline. In reading the readme one thing that has me ...
0 votes
1 answer
58 views

How to incorporate domain knowledge into a semantic segmentation network?

I'm working on a semantic segmentation project, and want to add some domain knowledge to the system. I want to ensure that for segmentation, there can only be one group of pixels that are predicted as ...
1 vote
1 answer
40 views

How to identify and diferentiate several edge lines of an object?

I want to create an AI to detect and identify certain edge lines on my image. The input image is a locker key, and I want to know the exact position of certain edges. Sample input image: Sample ...
  • 111
2 votes
0 answers
136 views

Why CNN inference works on larger images

I have been reading up on 'regular' CNN's such as Mask R-CNN, and as far as I understand it they rely on a fully connected layer in the end to classify pixels. FCN's (such as U-Net) which do not use ...
1 vote
1 answer
512 views

How does the classification head of EfficientDet work?

EfficientDet outputs classes and bounding boxes. My question is about both but specifically I am interested in the class prediction net part. In the paper's diagram it shows 2 conv layers. I don't ...
  • 11
-1 votes
1 answer
125 views

How to re-train an AI model to have smaller input image size

I need a PyTorch Model which can do road segmentation on OAK-D camera. The model provided requires Input Image Size: 896x512, which is too big for running on OAK-D camera. Thus I need to re-train it ...
  • 181
0 votes
0 answers
313 views

What to do when model stops learning after some epochs

I am training a segmentation model on 3D data, after around 170 epochs which took around 4 days, I notice the model is no more learning and the dice score is at 0.51. What is the best approach at this ...
0 votes
1 answer
307 views

Dissection of a depth map

I am curious about how depth maps work. While searching I came across this website which contains some images and their depth maps. I took this depth map and tried to study it using a python pillow. <...
  • 1,006
1 vote
2 answers
849 views

What is the difference (if any) between semantic segmentation and multi-class, mutually exclusive classification?

Multi-class classification is simply assigning all data points into one of up to any finite number of mutually exclusive labels. I am new to the field(s) of AI/ML and I keep hearing people use the ...
2 votes
0 answers
34 views

What is meant by Hinton when he refers to "Part-Whole Hierarchies" in his GLOM framework

I was recently reading Hinton's GLOM idea How to represent part-whole hierarchies in a neural network, and I am simply unsure about what exactly he means when he says parsing images into "part-...
1 vote
0 answers
65 views

Pixel values of segmap in multi-class semantic segmentation

I'm preparing a dataset for a multiclass semantic segmentation using U-Net like architecture. To be precise, I've got it ready but a question came to my mind. How does pixel values of a segmentation ...
  • 11
4 votes
1 answer
882 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 ...
2 votes
1 answer
3k views

What does the "number of channels" correspond to in U-Net?

I'm studying the U-Net CNN architecture. I'm new to CNNs and am confused regarding the "number of channels". Referring to the U-Net diagram, the input image is convolved with a 3x3 mask ...
  • 123
2 votes
0 answers
630 views

Semantic segmentation - background or ignore for non-target classes?

I am training a deep learning model for semantic segmentation. I am using the cityscapes dataset for training/evaluation. In cityscapes, there are 34 classes, and of which, we consider only 19 classes ...
  • 33
0 votes
1 answer
200 views

How should I incorporate numerical and categorical data as part of the inputs to the U-net for semantic segmentation?

I am using a U-Net to segment cancer cells in images of patients' arms. I would like to add patient data to it in order to see if it is possible to enhance the segmentation (patient data comes in the ...
  • 115
0 votes
1 answer
80 views

What are the state-of-the-art Person-Detektion / Human-Segmentation?

I would like to use a deep learning approach to detect people in videos. I have found some freely accessible implementations like Human Segementation with Pytorch or BodyPix / DeepLab / Pixellib with ...
  • 1
1 vote
1 answer
84 views

Why does my model not improve when training with mini-batch gradient descent, while it does with Adam?

I am currently experimenting with the U-Net. I am doing semantic segmentation on the 2018 Data Science Bowl dataset from Kaggle without any data augmentation. In my experiments, I am trying different ...
3 votes
3 answers
419 views

If I trained a model to perform semantic segmentation on images with only one object, would it also work on images with multiple objects?

I'm working on semantic segmentation tasks in the medical space using the U-Net. Let's say that I train a U-Net model on medical images with the goal of segmenting out, say, ligaments, from a medical ...
  • 131