Questions tagged [image-segmentation]
For questions related to image segmentation (in computer vision and related AI fields).
100
questions
0
votes
0
answers
10
views
Sketch-based segmentation attempt with Deep Learning
I'm looking for a deep-learning based segmentation capability, which should primarily consist of two steps:
The image to be examined contains certain structures, which are mainly defined by geometric ...
0
votes
1
answer
54
views
Is there way to segment an image without labeling/classification, as well as supervised learning?
Is there way to segment an image without labeling/classification, as well as supervised learning?
For an illustrative example, if one considers an image with a dog and a cup (we don't particularly ...
0
votes
0
answers
7
views
Quick Lightweight Image Segmentation Model For Training on Custom COCO-Format Dataset
I'm trying to build a model for image segmentation on a Raspberry Pi. I have a dataset with annotations in the COCO-format that took a long time to build, so I'd prefer not to have to build another ...
0
votes
0
answers
15
views
When generating segmentation mask, is it better for the ground truth mask to be a bit inside the object than outside?
I got asked this question today, and I was wondering.
When manually annotating images for ground truth, is it better for the model to get segmentation masks that are a bit inside the object or a bit ...
-1
votes
1
answer
37
views
What is exactly sparse annotation?
What is exactly sparse annotation? Is it different from labeling images?
I've been reading a paper about vessel segmentation and have some issues understanding this part.
0
votes
1
answer
40
views
Deep RL reward design for neuron centerline extraction task
As part of a bigger scope project, I'm training a RL agent that attempts to reconstruct, pixel by pixel, the trajectory of a neuron on a segmented image. To give a better insight on the task that I'm ...
0
votes
0
answers
50
views
Mask R-CNN: ground-truth vs target vs output masks
The mask branch of Mask R-CNN outputs masks of size $m\times m$ for each class ($k$ in total).
How are the outputted masks compared with the target masks, which in general have different sizes from $m\...
1
vote
0
answers
48
views
Mask R-CNN: how is the inference done?
According to the Mask R-CNN paper and the picture below (taken from the paper), the mask branch is computed in parallel with the bbox classification and regression branches.
However in the paper they ...
1
vote
2
answers
66
views
Image segmentation when given masking information is incomplete
In my problem, there are about 5,000 training images and there are about 50~100 objects of identical type (or class) on average, per image. And for each training images, there is a partial mask ...
3
votes
1
answer
51
views
Custom Tensorflow loss function that disincentivizes all black pixels
I'm training a Tensorflow model that receives an image and segments the image into foreground and background. That is, if the input image is w x h x 3, then the ...
0
votes
0
answers
49
views
Why is the simplest U-Net architecture giving the best (but not good enough) results on a multi-class segmentation on microscopic data?
Currently, I'm trying to optimize a training process of a neural net to improve final results. The problem I'm dealing with is multiclass segmentation on microscopic data.
The paradox is that the best ...
1
vote
0
answers
39
views
Is there any way to remove background of an image fully with the help of post-processor techniques(like edge detector) after deep learning based model
I'm using a deep learning-based model (deep lab v3+ with xception as the backbone) for image segmentation and removing the background. The subject of the image will be a person. And my target is to ...
0
votes
0
answers
20
views
How to Train Big Size Image and Predict Various Size of Images
I don't have deep knowledge of the neural network, but I would like to segment the road from UAV images and detect cracks on them.
My first question:
I am planning to do fine-tuning from pre-trained ...
0
votes
0
answers
48
views
Which neural network architecture to use to detect very close and very small blobs in high resolution fluorescence images?
Context
I am developing a pipeline to automate the detection of small, almost circular, bright blobs (4px) (see first image below) on high-resolution fluorescence images (2048px) and later to assign ...
0
votes
1
answer
34
views
How to divide a segmented image into classes instances?
Is there a method/algorithm to generate instances of objects from image that was segmented by the use of any image segmentation models?
For example, I have an image with one class and it was segmented ...
0
votes
0
answers
11
views
How to properly report results for a medical image segmentation task?
Let’s consider a 2-class / binary segmentation problem where c=0 for background (healthy tissues) and c=1 for foreground (...
0
votes
1
answer
32
views
Should I label static objects on video dataset?
I'm using nvidia Transfer Learning Toolkit to detect cars in some video frames.
I found some dataset (for example https://www.jpjodoin.com/urbantracker/dataset.html and https://www.kaggle.com/...
-1
votes
1
answer
49
views
How to re-training an AI model to have smaller input image size
I need a PyTorch Model which can do road segmentation on OAK-D camera.
The model provided requires Input Image Size: 896*512, which is too big for running on OAK-D camera. Thus I need to re-training ...
1
vote
1
answer
39
views
Aside from dice score, what other good metrics are used to evaluate segmentation models?
I have a segmentation which outputs only one channel image (2 class segmentation). I have used dice score for most of the time, but now higher powers in my team want me to expand evaluation metrics ...
0
votes
0
answers
26
views
Any papers or implementations of Multi label segmentation in pytorch/keras
I am currently working on a project related to Multi label segmentation. I haven't been able to find any substantial papers where objects in images were segmented based on a membership function. For ...
0
votes
1
answer
87
views
Dissection of a depth map
I am curious about how depth maps work. While searching I came across this website which contains some images and their depth maps. I took this depth map and tried to study it using a python pillow.
<...
0
votes
0
answers
30
views
What are the existing AI methods to approach 3D volumes of computed tomography?
I have a dataset which consists of computed tomography images (CT scans) of parts that contain pores and cracks. The sets for each part are of about 1100 * 1100 * 3000-ish resolution. Currently, I use ...
0
votes
0
answers
13
views
Segmenting an instance of an object based on training with small dataset of similar objects and background
I am seeking for your advice with the topic related to segmentation.
Imagine the flying bird in the sky and a man taking a picture of that bird every second. There is very little change happening to ...
0
votes
0
answers
12
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 ...
0
votes
0
answers
50
views
Anything similar to BERT but for pixel-wise embedding in images
In NLP there is BERT which can take a sentence and turn it into an embedding (vector representation) which in some ways encompasses the "meaning" or more precisely the context of the ...
0
votes
0
answers
14
views
Why do the authors of this paper down-sample by $ds_1 / 2$ (in the context of coarse-to-fine segmentation)?
This question is a follow-up of this post and based on this paper. In section 2.2, the authors write:
In the first level, the 3D FCN is trained on images of the lowest resolution in order to capture ...
1
vote
1
answer
107
views
What does 'downsampling' and 'upsampling' mean in coarse-to-fine segmentation?
The paper here in section 2.1 Coarse-to-fine prediction:
To increase the field of view presented to the CNN and reduce the
redundancy among neighboring voxels, each image is downsampled by a factor ...
0
votes
0
answers
31
views
How to improve the Loss and Learning curves and smoothen them
I am fairly new to deep learning and I have been testing out several architectures for the segmentation task of clouds in satellite imagery. I am using a simple Unet as my benchmark, Unet++, Efficient ...
2
votes
0
answers
18
views
Predicting the the motion of a 3D object when the motion of a set of markers is known
trying to figure out where to get started with this:
I have a few hundred CT images where certain three-dimensional features in the image (anatomy) are moving in a correlated fashion with a set of ...
1
vote
2
answers
1k
views
Unet Overfitting for binary segmentation of fake images
I am working on a project where I am trying to detect and localize forgeries in images. I am using the CASIA v2 dataset and using Unet model for the task. I have the binary masks of all the images in ...
2
votes
0
answers
229
views
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 ...
0
votes
0
answers
20
views
Why doesn't U-Net work with images different from the dataset?
I have implemented a U-Net, similar to this implementation, but for a different dataset, this one, to segment roads.
It works fine using the test folder images, but, for example, when I pick a print ...
1
vote
1
answer
44
views
How to use mixed data for image segmentation?
I have a task for which I have to do image segmentation (cancer detection on MRIs). If possible, I would also like to include clinical data (i.e. numeric/categorical data which comes in the form of a ...
0
votes
1
answer
36
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 ...
3
votes
1
answer
131
views
How to incorporate a symmetry constraint in the loss function to train a CNN?
I have a task of extremely sparse binary segmentation, i.e. the segmentation mask contains either 0 or 1, and there are ~95% zeros and only ~5% ones. I use the focal loss to address the sparseness (...
1
vote
0
answers
30
views
What does Dice Loss should receive in case of binary segmentation
I implemented Dice loss class in pytorch:
...
2
votes
0
answers
48
views
How and why do state-of-the-art models in medical segmentation differ from general segmentation models?
I am just getting into medical image segmentation and have been able to understand the state-of-the-art architectures, like Double UNet, UNet++, and Multiresunet.
What I haven't understood yet: Why ...
1
vote
1
answer
138
views
Have I understood the loss function from the original U-Net paper correctly?
In the original U-Net paper, it is written
The energy function is computed by a pixel-wise soft-max over the final
feature map combined with the cross entropy loss function.
...
$$
E=\sum_{\mathbf{x} ...
-1
votes
2
answers
69
views
Semantic segmentation CNN outputs all zeroes
I'm using MATLAB 2019, Linux, and UNet (a CNN specifically designed for semantic segmentation). I'm training the network to classify all pixels in an image as either cell or background to get ...
3
votes
1
answer
131
views
What is the use of the regular convolutional layer in expansion path of U-Net?
I was going through the paper on U-Net. U-net consists of a contracting path followed by an expanding path. Both the paths use a regular convolutional layer. I understand the use of convolutional ...
1
vote
1
answer
79
views
Training a classifier on different datasets with different image conditions for different labels causes the model to infer using the background
I have an interesting problem related to training the model on two different datasets for the target feature on images taken on different conditions, which might affect the model's ability to ...
1
vote
1
answer
54
views
How does general image background removal AI work?
I'm well aware of the inner workings of CNN models for object detection, and although I've not worked on a semantic segmentation problem I can imagine how it works.
With these types of models, we need ...
7
votes
1
answer
110
views
Validation accuracy higher than training accurarcy
I implemented the unet in TensorFlow for the segmentation of MRI images of the thigh. I noticed I always get a higher validation accuracy by a small gap, independently of the initial split. One ...
0
votes
1
answer
50
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 ...
2
votes
0
answers
32
views
Loss function decays linearly in segmentation MRI fascia
I am working on a segmentation of MRI images of the thigh. I am trying to segment the fascia, there is a slight imbalance between the background and the mask. I have about 1400 images from 30 patients ...
1
vote
0
answers
33
views
How can I improve the performance on unseen data for semantic segmentation using an auto-encoder?
I am using simple autoencoders for the task of semantic segmentation on the VOC2012 dataset. I am currently using a simple autoencoder based model. It is trained on adam optimizer with cross-entropy ...
0
votes
0
answers
44
views
Is Webpage Semantic Segmentation possible nowadays?
I'm trying to do some research about semantic segmentation for webpages, in particular e-commerce webpages. I found some articles which provide some solutions based on very old dataset and those ...
1
vote
0
answers
31
views
Could the data augmentation lead to the model learning features which corresponds to data augmented data and not to the real data?
I am trying to train a Unet network with Synthetic data to do binary segmentation due to the fact that is is not easy to collect real data.
And there is something in the training process that I do not ...
1
vote
0
answers
402
views
Getting bounding box/boundaries from segmentations in UNet Nuclei Segmentation
From my understanding, in a tissue where nuclei are present and need to be detected, we need to predict bounding boxes (either rectangular/circular or in the shape of the nucleus, i.e. as in instance ...
1
vote
0
answers
67
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 ...