16 votes
Accepted

What is a fully convolution network?

Fully convolution networks A fully convolution network (FCN) is a neural network that only performs convolution (and subsampling or upsampling) operations. Equivalently, an FCN is a CNN without fully ...
user avatar
  • 33.8k
13 votes
Accepted

How can I deal with images of variable dimensions when doing image segmentation?

There are 2 problems you might face. Your neural net (in this case convolutional neural net) cannot physically accept images of different resolutions. This is usually the case if one has fully-...
user avatar
  • 384
6 votes

What do the words "coarse" and "fine" mean in the context of computer vision?

tl;dr What does that mean in the context of this paper? With "coarse segmentation" the author means a segmentation that doesn't have much detail. "Fine segmentation", on the other hand, refers to ...
user avatar
  • 3,093
3 votes

What is the use of the regular convolutional layer in expansion path of U-Net?

The point is that in the expansive path you have two forms of information: the information from the contracting path, which includes all high-level features extracted from the original image. the ...
user avatar
  • 3,093
3 votes

What are the best algorithms for image segmentation tasks?

U-Net and U-Net inspired architectures have been quite popular in the medical image-related tasks ever since it was first introduced. There have been several improved versions of U-Net designed for ...
user avatar
3 votes

Do models train better if the labelling information is more specific (or dense)?

It depends on what is your ultimate goal. If your goal is to simply classify the object in the image, having more complex output won't help. Simpler output representation yields better result. If your ...
user avatar
  • 1,715
3 votes
Accepted

What are some references that describe known filters (or kernels) and how we can create new ones?

I'd suggest you better understand edge detectors such as Robert or Sobel operators first to understand better how convolution operation on images extract features by constant value kernels. Would ...
user avatar
  • 1,359
2 votes

How can I deal with images of variable dimensions when doing image segmentation?

You could also have a look at the paper Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (2015), where the SPP-net is proposed. SSP-net is based on the use of a "...
user avatar
2 votes

Which evaluation methods can I use for image segmentation?

See: Martin Thoma: A Survey of Semantic Segmentation, Section III Subsection A is about metrics and B is about datasets. Metrics include: accuracy, IoU, frequency weighted IoU, F-beta score, ...
user avatar
  • 1,007
2 votes
Accepted

What make a CNN suitable for image classification or semantic segmentation?

Disclaimer: This question is very broad, my answer is admittedly partial and is intended to just give an idea of what's out there and how to find out more. How do you "say" a network: "classify me ...
user avatar
  • 171
2 votes
Accepted

Why everyone is using CNN for image segmentation?

CNN is used since it is effectively an optimized use case for dealing with image data. CNN effectively automatically extracts features from images. Other techniques are more likely to not take full ...
user avatar
2 votes
Accepted

How many ways are there to perform image segmentation?

Apart from the multitudes of traditional image segmentation techniques (Watershed, Clustering or Variational methods), newer Segmentation schemes using Deep Learning are actively being used, which ...
user avatar
  • 188
2 votes

Best approach for 2D Grid Image Segmentation

This is a really cool problem. You already have a working model here are a few different ways of going forward with the project. Grouping text based on locality. "no segmentation" Text region ...
user avatar
2 votes
Accepted

How to incorporate a symmetry constraint in the loss function to train a CNN?

If you know it is symmetric, then you could do a couple things. Zero out a half. Don't bother learning both halves of the image. Just put a zero mask over the upper or lower half of the output ...
user avatar
2 votes
Accepted

Custom Tensorflow loss function that disincentivizes all black pixels

The background being an unbalance class is a well known problem in image segmentation. Before digging into custom losses you should take a look to existing ones that address this specific issue like ...
user avatar
2 votes

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

I don't think that more advanced AI would necessarily produce more consistent results. Check something as simple as the Prewitt operator, which is pretty damn good at edge detection. I would suggest ...
user avatar
1 vote
Accepted

How to use mixed data for image segmentation?

You can try doing image segmentation the traditional way, just using the image data. If you want to use the non-image data, then, you can introduce classification as another task for your network. It ...
user avatar
1 vote
Accepted

Have I understood the loss function from the original U-Net paper correctly?

Yes, $E$ is the cross-entropy function and a direct generalization of the binary case. For the binary case, probability to belong to the class $1$ is given by a sigmoid function $\sigma(x)$ of the ...
user avatar
1 vote

Semantic segmentation CNN outputs all zeroes

Similar to other answers, I don't know Matlab that well but you could try the following steps to debug your problem. Make sure you can overfit to a single instance from your dataset, pull out a single ...
user avatar
1 vote
Accepted

Training a classifier on different datasets with different image conditions for different labels causes the model to infer using the background

I am afraid that the model will infer from the background information that it shouldn't use to predict the plant diseases, what makes the problem worse is that some plant diseases only exist in one ...
user avatar
1 vote

How does general image background removal AI work?

In image segmentation the target is actually an image, with the same dimensions as the input, where each pixel has a label depending on which class it represents. It is not uncommon for such a dataset ...
user avatar
  • 3,093
1 vote

How to create vector representation of roadmap like scans

It turned out that my intuition was not far off. The skeletonization is a good step. The Hough transform though is not a good way to create a graph of the roadmap. It seems that the Ramer–Douglas–...
user avatar
  • 121
1 vote

How to use 'Canny/Watershed' algorithm's output as an input for Image Classification Model

First and foremost, I have to say that this could (and likely will) be a very hard task. Neural networks (NNs) have excelled at computer vision tasks identifying everything from textures to complex ...
user avatar
  • 156
1 vote

Can neural network help me with detecting center coordinates of particles in an image?

This is a very hard problem, you have many overlapping points with objects which aren't completely round. I'm not very knowledgeable on CV but I suspect you will find it very challenging. I would ...
user avatar
1 vote
Accepted

How do I generate a feature representation of a saliency map (or mask)?

I found a method to do it in the paper Cross-Modality Personalization for Retrieval (2020, accessed: 20-Feb-2020). Representation. For images, we extract Inception-v4 CNN features [36]. We then ...
user avatar
1 vote

What are the best algorithms for image segmentation tasks?

You can find leaderboards as well as code at this address. For now, HRNetV2 leads the game. The U-Net architecture is part of a broad family of network architectures that aggregate multi-scale ...
user avatar
  • 298
1 vote

“Outside-in” versus “Inside-out” machine learning

It sounds like you are interested in the ideas of intrinsic motivation and attention in the context of machine learning. These are big topics, and the subject of much active research. Intrinsic ...
user avatar
1 vote
Accepted

How to add some data input in a CNN?

If your interest is positional information, encode it! This could include learning an embedding for each position and leveraging that in your model. You could also use an approach to hard-encode ...
user avatar
  • 2,249
1 vote

Which evaluation methods can I use for image segmentation?

The paper referenced by Martin Thoma is the go-to for semantic segmentation. However I will also like to add the Panoptic Segmentation metric as an aggregated method to measure both the detection task ...
user avatar
  • 1,018
1 vote

How can I deal with images of variable dimensions when doing image segmentation?

Try resizing the image to the input dimensions of your neural network architecture(keeping it fixed to something like 128*128 in a standard 2D U-net architecture) using nearest neighbor interpolation ...
user avatar

Only top scored, non community-wiki answers of a minimum length are eligible