4 votes
Accepted

Why is my training loss not changing?

Dying ReLU is a good guess. But the question is why this is not happening in original paper. Answer is input data features. Have you normalize the data? You can debug this issue by trying to find the ...
Enes Kuz's user avatar
3 votes
Accepted

What is Deep supervision?

Partial answer: Quoting a paper "The advantage of such deep supervision is evident: (1)for small training data and relatively shallower networks, deep supervision functions as a strong “...
Noah Weber's user avatar
  • 5,669
2 votes

Is there an official procedure to compute mIoU?

I came across this very question myself while I was trying to replicate the results reported on a paper relevant to semantic segmentation. It turns out there is not really a universal way of computing ...
Yiannis Ath's user avatar
2 votes

How do you train a semantic segmentation model to optimize for IoU rather than accuracy?

You could directly optimize the mean IoU loss by implementing the following loss: ...
hh32's user avatar
  • 2,732
2 votes

What is Deep supervision?

The idea of deep supervision is to add, so called, companion objective functions at each hidden layer of a network and then compute the final loss as the output loss plus the sum of the companion ...
Smajjk's user avatar
  • 121
1 vote

Building a CNN (with Keras for pixelwise classification)

The last layer should match the dimension of your response. Dense layer can only return 1D whereas conv layers can return 2D., Based on your question, you want to classify all your pixels (binary?) in ...
Max's user avatar
  • 31
1 vote
Accepted

Why not using segmentation architectures for object detection?

At the end of the day, if an architecture satisfies your goal, you should use it. If you can detect objects using a segmentation model, go ahead. But that's where practice differs from theory. Don't ...
Valentin Calomme's user avatar
1 vote
Accepted

Remove frame from background

MODNet, based on the paper, is a network that removes the background entirely just as if the person is standing in front of a green screen. And I assume that is why you are left only with the player ...
Lars's user avatar
  • 120
1 vote

Tool for annotation of images for semantic segmentation

Diffgram is really great for this! I used it for a construction monitoring project. It's Open Source. From their site: Semantic Segmentation Tools: Auto Bordering: Automatically detects edges to ...
oooiiiii's user avatar
  • 111
1 vote

How to extract contents by topic from a document?

Here are a list of tools you can look into: https://tika.apache.org/ https://jsoup.org/ https://poi.apache.org/ This was a neat read detailing the steps. The author was doing something similar to ...
Keneni's user avatar
  • 111
1 vote
Accepted

Semantic networks: word2vec?

There are a few models that are trained to analyse a sentence and classify each token (or recognise dependencies between words). Part of speech tagging (POS) models assign to each word its function (...
RonsenbergVI's user avatar
  • 1,024
1 vote
Accepted

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

So the question asks about why different loss function lead to different error scores. So globally error is there to help us measure the level of discrimination between the output of the model and the ...
shepan6's user avatar
  • 1,428
1 vote

resnet50 implementation for semantic segmentation

The output from the ResNet model is a vector containing the probability that the image belongs to each of the n classes, in your case to any of the 21 classes. If ...
Oxbowerce's user avatar
  • 7,307
1 vote

My semantic segmentation model classifies everything as background

This answer might be a little late, but I believe that what you need is the Focal Tversky Loss (https://arxiv.org/abs/1810.07842). Neither the vanilla Focal Loss nor the Dice Loss generalize well for ...
mnobrecastro's user avatar
1 vote

My semantic segmentation model classifies everything as background

Are you using some data augmentation with random crops / rotations / zooms ? If you do, you might have some images with only background labels and if so I would suggest you to add a condition to only ...
y-prudent's user avatar
1 vote
Accepted

Suitable instance counting CNN for training on polygonal masks

Which CNN should I use for instance counting given that my dataset consists of labeled polygons? CNNs for instance segmentation. To start with you can try Mask-RCNN. Here are all state of the art ...
Devashish Prasad's user avatar
1 vote

High image segmentation metrics after training but poor results in prediction

I agree the metrics between your test set and validation set are quite close, but looking at your code it seems you may have run for the full 100 epochs. ...
fswings's user avatar
  • 378
1 vote

High image segmentation metrics after training but poor results in prediction

The coefficients are reported on your 150 training examples? This looks like a textbook example of overfitting: good performance on training data, bad on test data. The U-net model has a large number ...
Paul's user avatar
  • 903
1 vote
Accepted

Criteria for saving best model during training neural network?

The loss is mostly a measure that helps the model learn and is not looked at too much when deciding which model to select. A more business oriented measure is often used for this, e.g. accuracy. Since ...
Oxbowerce's user avatar
  • 7,307
1 vote
Accepted

Semantic segmentation of an image with multiple labels per pixel

Three separate models (one per channel) will easily learn to predict the >channel category, but it will never output r0g1b2 and r2g3b0 classes in 64 class model because it have never seen these ...
Fab's user avatar
  • 49

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