Skip to main content

All Questions

18 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4 votes
0 answers
57 views

What are some neural network models that can use auxiliary info during training for image segmentation?

What are some deep learning models that can use supplementary information other than RGB channels for image segmentation? For example, imagine a poorly shot image of a river (blue) that shows a gap, ...
Nanako Honda's user avatar
2 votes
1 answer
147 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 ...
miimi's user avatar
  • 21
2 votes
0 answers
299 views

What is the difference between using a backbone architecture and transfer learning?

I'm super new to deep learning and computer vision, so this question may sound dumb. In this link (https://github.com/GeorgeSeif/Semantic-Segmentation-Suite), there are pre-trained models (e.g., ...
Jon.O's user avatar
  • 21
2 votes
0 answers
224 views

How to train image segmentation task with only one class?

Is there a neural network that has architecture optimizations for segmenting only one class (object and background)? I have tried U-net but it is not providing good enough results. I am wondering if ...
Dusan J.'s user avatar
  • 129
2 votes
0 answers
214 views

Confidence Maps and Non-Linearity

I am currently trying to improve a CNN architecture that was proposed for generating depth images. The architecture was originally proposed for autonomous driving and it looks like following : The ...
3yanlis1bos's user avatar
1 vote
0 answers
67 views

Visualization of Transposed Convolutions

After reading on Transposed Convolutions and Fully Convolutional Networks in the d2l book (14.10 and 14.11), I wondered about the visualization of transposed convolutions. As you probably know, ...
Mathy's user avatar
  • 153
1 vote
0 answers
30 views

Latest status on stability of CNN architectures to noise and "clever hans" issues

I was working with CNN architectures for image segmentation a few years ago, and I remember there was a big concern about on the stability of the predicted masks due to the introduction of small ...
krishnab's user avatar
  • 207
1 vote
0 answers
146 views

Training a CNN for semantic segmentation of large 4600x4600px images

I am trying to implement a CNN (U-Net) for semantic segmentation of similar large grayscale ~4600x4600px medical images. The area I want to segment is the empty space (gap) between a round object in ...
Gioni's user avatar
  • 11
1 vote
0 answers
25 views

Model output segmentation maps which are not full

I created a VGG based U-Net in order to perform image segmentation task on yeast cells images obtained by a microscope. There are a couple of problems with the data: There is inhomogeneity in the ...
David's user avatar
  • 188
1 vote
0 answers
90 views

Extending patch based image classification into image classification

I am trying to classify tampered, pristine images from set of images, in that I have built a network in which I would divide the image into multiple overlapping patches and then classify them into ...
kiran's user avatar
  • 21
1 vote
0 answers
97 views

How can the FCNN reduce the dimensions of the input from $1048 \times 100$ to $523 \times 100$ with max-pooling?

I am trying to implement a paper on Image tempering detection and localization, the paper is Image Manipulation Detection and Localization Based on the Dual-Domain Convolutional Neural Networks, I was ...
kiran's user avatar
  • 21
1 vote
0 answers
225 views

Suppress heatmap non-maxima in segmentation with UNet

I'm using U-Net for image segmentation. The model was trained with images that could contain up to 4 different classes. The train classes are never overlapping. The output of the UNet is a heatmap (...
luke88's user avatar
  • 111
1 vote
0 answers
24 views

Super-Resolution with Convolutional Neuronal Networks, why interpolation at the beginning?

I have read several papers about super-resolution with CNNs, where a low-resolution image is reconstructed to a high-resolution image. What I don't understand is, why it is necessary to interpolate ...
Khan's user avatar
  • 175
1 vote
0 answers
76 views

Using U-NET for image semantic segmentation

I'm getting literally crazy trying to understand how U-NET works. Maybe it is very easy, but I'm stuck (and I have a terrible headache). So, I need your help. I'm going to segment MRI to find white ...
VansFannel's user avatar
1 vote
0 answers
150 views

How to measure the size of an crack which is segmented from an image using Mask-RCNN?

I am a masters student going to work in a project to analyze the cracks in underwater concrete structures. I need some suggestions for data acquisition and length measurement of the crack. I have ...
ovezn's user avatar
  • 61
0 votes
1 answer
76 views

How to add engineered features to an image segmentation model

I have built a U-net model for image segmentation of 3-channel remote sensing images. I have a total of four classes; two of these classes look very similar and are hard to distinguish in the images ...
Ellio's user avatar
  • 1
0 votes
1 answer
266 views

Semantic segmentation failing in small instance detection

I performed semantic segmentation with U-net. My dataset consists of grayscale images of defects. After training the dataset for I got an metric accuracy of only 0.3 - 0.4 IOU. Eventhough it is merely ...
shankar ram's user avatar
-1 votes
0 answers
20 views

How to change a single object detection network to a multiple object detection network?

I have trained a CNN network to detect a circle and approximate its centre and radius in an image. What I want to do now is detect the centre and radius of all the circles if there are multiple ...
Ravish Jha's user avatar