Stack Overflow
Stack Overflow

Questions tagged [semantic-segmentation]

Semantic segmentation is the task of classifying every pixel in the image to a category or class label.

Semantic segmentation is the task of classifying every pixel in the image to a category. It refers to the process of linking each pixel in an image to a class label. Some of its primary applications are in autonomous vehicles, human-computer interaction & robotics.

532 questions
105
votes
3 answers

What is "semantic segmentation" compared to "segmentation" and "scene labeling"?

Is semantic segmentation just a Pleonasm or is there a difference between "semantic segmentation" and "segmentation"? Is there a difference to "scene labeling" or "scene parsing"? What is the difference between pixel-level and pixelwise…
Martin Thoma
  • 124,992
  • 159
  • 614
  • 958
18
votes
3 answers

Deploy Semantic Segmentation Network (U-Net) with TensorRT (no upsampling support)

I am trying to deploy a trained U-Net with TensorRT. The model was trained using Keras (with Tensorflow as backend). The code is very similar to this one: https://github.com/zhixuhao/unet/blob/master/model.py When I converted the model to UFF…
Yayuchen
  • 301
  • 3
  • 6
14
votes
2 answers

Can i finetune deeplab to a custom dataset in tensorflow?

I would like to customize deeplab for image segmentation using my own dataset ? Is this achievable by retraining ?
mrBean
  • 183
  • 1
  • 9
13
votes
1 answer

What is imbalance in image segmentation?

I know the imbalance in an image classification problem such as the cat vs dog classification，if there are too many cat images and too few dog images. But I don't know how to adress an imbalance in a segmentation problem. For example，my task is to…
spider
  • 909
  • 1
  • 11
  • 19
11
votes
2 answers

Loss Function is decreasing but metric function remains constant?

I am working on Medical Image Segmentation. I have two classes. class 0 as background and class 1 as a lesion. As the dataset is highly unbalanced, I am using loss function as (1 - weighted Dice coefficient) and metric function as dice coefficient.…
Md Sharique
  • 111
  • 5
11
votes
1 answer

How is the smooth dice loss differentiable?

I am training a U-Net in keras by minimizing the dice_loss function that is popularly used for this problem: adapted from here and here def dsc(y_true, y_pred): smooth = 1. y_true_f = K.flatten(y_true) y_pred_f = K.flatten(y_pred) …
zucchinifries
  • 523
  • 6
  • 13
11
votes
2 answers

Intuition behind U-net vs FCN for semantic segmentation

I don't quite understand the following: In the proposed FCN for Semantic Segmentation by Shelhamer et al, they propose a pixel-to-pixel prediction to construct masks/exact locations of objects in an image. In the slightly modified version of the…
Jonathan
  • 1,876
  • 2
  • 20
  • 56
10
votes
2 answers

Correct way to use custom weight maps in unet architecture

There is a famous trick in u-net architecture to use custom weight maps to increase accuracy. Below are the details of it: Now, by asking here and at multiple other place, I get to know about 2 approaches. I want to know which one is correct or is…
Beginner
  • 721
  • 11
  • 27
10
votes
1 answer

ImageDataGenerator for semantic segmentation

I am trying to do semantic segmentation with Keras and when trying to load the images i get this error using flow_from_directory method. Found 0 images belonging to 0 classes. Found 0 images belonging to 0 classes. This is my code. from…
Jaime Cuellar
  • 464
  • 1
  • 5
  • 20
10
votes
1 answer

Semantic Segmentation Loss functions

Does it make sense to combine cross-entropy loss and dice-score in a weighted fashion for a binary segmentation problem ? Optimizing the dice-score produces over segmented regions, while cross entropy loss produces under-segmented regions for my…
HuckleberryFinn
  • 1,489
  • 2
  • 16
  • 26
10
votes
1 answer

Generalized dice loss for multi-class segmentation: keras implementation

I just implemented the generalised dice loss (multi-class version of dice loss) in keras, as described in ref : (my targets are defined as: (batch_size, image_dim1, image_dim2, image_dim3, nb_of_classes)) def generalized_dice_loss_w(y_true, y_pred):…
Manu
  • 186
  • 3
  • 11
9
votes
3 answers

How to set heatmap aspect ratio

I have a single-channel image where each integer pixel value maps to a string. For example 5 -> 'person'. I'm trying to create an interactive image where hovering over a pixel will display it's corresponding string. I figured using plotly heatmaps…
Austin
  • 6,921
  • 12
  • 73
  • 138
9
votes
2 answers

Can Caffe classify pixels of an image directly?

I would like to classify pixels of an image to "is street" or "is not street". I have some training data from the KITTI dataset and I have seen that Caffe has an IMAGE_DATA layer type. The labels are there in form of images of the same size as the…
Martin Thoma
  • 124,992
  • 159
  • 614
  • 958
8
votes
2 answers

Plotting multi-class semantic segmentation transparent overlays over RGB image

I have the results of semantic segmentation masks (values between 0-1, requiring otsu thresholding to determine what's positive) which I'd like to plot directly on the RGB image with different random color per prediction class on an RGB image. I…
AMM
  • 2,195
  • 2
  • 20
  • 28
8
votes
1 answer

How to retrieve the labels used in a segmentation mask in AWS Sagemaker

From a segmentation mask, I am trying to retrieve what labels are being represented in the mask. This is the image I am running through a semantic segmentation model in AWS Sagemaker. Code for making prediction and displaying mask. from…
Dre
  • 713
  • 1
  • 8
  • 27
1
2 3
…
35 36