Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [semantic-segmentation]

25 questions
4
votes
1 answer

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 image has 2 people on it, it would output a mask…
dato nefaridze
  • 882
  • 10
  • 22
4
votes
3 answers

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 image. If I train that model on images that…
cmed123
  • 141
  • 2
2
votes
0 answers

How do I use a 2D image segmentation model on 3D medical imaging data?

I am trying to use a high-level semantic segmentation model (something like DeepLabv3), that takes in 2D RGB images, and then fine-tune it for my problem. However, I am working with brain MRI images which are grayscale 3D images. The obvious…
Tarek Alkabbani
  • 21
  • 1
2
votes
0 answers

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 these layers are able to effectively process…
Cartman123
  • 121
  • 2
2
votes
0 answers

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-whole hierarchies". Moreover, wouldn't semantic…
ElectricMinimum58
  • 21
  • 1
2
votes
1 answer

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 which generates a 570x570 output. This output image is then…
Izzo
  • 123
  • 1
  • 5
2
votes
0 answers

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 and the rest of the classes are ignored. For…
147956
  • 33
  • 2
2
votes
1 answer

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 Tensorflow. They all work well, but with many it…
miimi
  • 21
  • 1
1
vote
1 answer

How do I input multi-channel Numpy array to U-net for semantic segmentation

I had lidar 3D point cloud data from semantckitti. I want to perform Semantic Segmentation on the data using U-Net. I converted the 3d point cloud data into 2D using spherical conversion and saved the original point cloud data which was in (.bin…
Leibniz 24
  • 11
  • 1
1
vote
1 answer

Why do we do need compression in Semantic Segmentation?

When doing semantic segmentation, we often make use of FCN, which can be thought of in two parts: an encoder and decoder. As I understand, the encoder compresses the image into a spatially small, but high number of channels. The decoder then uses…
Dude156
  • 113
  • 4
1
vote
0 answers

Resizing segmentation masks

I am trying to run a semantic segmentation model. The problem is, my data has different resolution for every image and for corresponding segmentation map (image and corresponding segmentation map have same aspect ratio. But aspect ratio changes for…
programmer_04_03
  • 73
  • 8
1
vote
1 answer

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 output image. As output i have each red line…
Lluis C
  • 111
  • 3
1
vote
1 answer

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 understand the code and how it works. And what's the…
ML Dev
  • 11
  • 3
1
vote
3 answers

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 term "semantic segmentation." I want to "translate"…
tdMJN6B2JtUe
  • 115
  • 7
1
vote
0 answers

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 map influence the training? Also, is it better to…
Nuwanda
  • 11
  • 2
1
2