Generative adversarial networks for multiple distribution noise removal
$begingroup$
I am working on a project where I need to denoise images, and my dataset is composed of a big chunk of pairs <natural image, same image with synthetically added noise>. The fact is, I have multiple sources of noise (with labels), e.g. Gaussian noise, salt&pepper, distortion, saturation to name a few. Different noises types are on the same original images, meaning that for each undistorted image, I have one pair for each noise type, which I believe is relevant for training.
Thanks to the recent success of GANs for image translation tasks, I was looking into recent architectures and how I can adapt them for my task. The question is: do you think that is possible for a GAN to learn a many-to-one mapping between distributions, i.e. different noise distributions (the many) and the undistorted image distribution (the one) or do I need to train multiple networks for different kinds of noise?
Given that I have paired images I was looking into the pix2pix architecture. What about the recent CycleGAN? Learning the backward mapping function looks a lot tougher if there are multiple distributions, which I guess is why when they release the pre-trained models they indeed have multiple models for multiple tasks.
machine-learning computer-vision gan generative-models
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
asked Feb 26 '18 at 2:05
powderpowder
1011
$endgroup$
add a comment |
$begingroup$
I am working on a project where I need to denoise images, and my dataset is composed of a big chunk of pairs <natural image, same image with synthetically added noise>. The fact is, I have multiple sources of noise (with labels), e.g. Gaussian noise, salt&pepper, distortion, saturation to name a few. Different noises types are on the same original images, meaning that for each undistorted image, I have one pair for each noise type, which I believe is relevant for training.
Thanks to the recent success of GANs for image translation tasks, I was looking into recent architectures and how I can adapt them for my task. The question is: do you think that is possible for a GAN to learn a many-to-one mapping between distributions, i.e. different noise distributions (the many) and the undistorted image distribution (the one) or do I need to train multiple networks for different kinds of noise?
Given that I have paired images I was looking into the pix2pix architecture. What about the recent CycleGAN? Learning the backward mapping function looks a lot tougher if there are multiple distributions, which I guess is why when they release the pre-trained models they indeed have multiple models for multiple tasks.
machine-learning computer-vision gan generative-models
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
asked Feb 26 '18 at 2:05
powderpowder
1011
$endgroup$
add a comment |
$begingroup$
I am working on a project where I need to denoise images, and my dataset is composed of a big chunk of pairs <natural image, same image with synthetically added noise>. The fact is, I have multiple sources of noise (with labels), e.g. Gaussian noise, salt&pepper, distortion, saturation to name a few. Different noises types are on the same original images, meaning that for each undistorted image, I have one pair for each noise type, which I believe is relevant for training.
Thanks to the recent success of GANs for image translation tasks, I was looking into recent architectures and how I can adapt them for my task. The question is: do you think that is possible for a GAN to learn a many-to-one mapping between distributions, i.e. different noise distributions (the many) and the undistorted image distribution (the one) or do I need to train multiple networks for different kinds of noise?
Given that I have paired images I was looking into the pix2pix architecture. What about the recent CycleGAN? Learning the backward mapping function looks a lot tougher if there are multiple distributions, which I guess is why when they release the pre-trained models they indeed have multiple models for multiple tasks.
machine-learning computer-vision gan generative-models
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
asked Feb 26 '18 at 2:05
powderpowder
1011
$endgroup$
I am working on a project where I need to denoise images, and my dataset is composed of a big chunk of pairs <natural image, same image with synthetically added noise>. The fact is, I have multiple sources of noise (with labels), e.g. Gaussian noise, salt&pepper, distortion, saturation to name a few. Different noises types are on the same original images, meaning that for each undistorted image, I have one pair for each noise type, which I believe is relevant for training.
Thanks to the recent success of GANs for image translation tasks, I was looking into recent architectures and how I can adapt them for my task. The question is: do you think that is possible for a GAN to learn a many-to-one mapping between distributions, i.e. different noise distributions (the many) and the undistorted image distribution (the one) or do I need to train multiple networks for different kinds of noise?
Given that I have paired images I was looking into the pix2pix architecture. What about the recent CycleGAN? Learning the backward mapping function looks a lot tougher if there are multiple distributions, which I guess is why when they release the pre-trained models they indeed have multiple models for multiple tasks.
machine-learning computer-vision gan generative-models
machine-learning computer-vision gan generative-models
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
asked Feb 26 '18 at 2:05
powderpowder
1011
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
asked Feb 26 '18 at 2:05
powderpowder
1011
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
edited Feb 26 '18 at 2:09
Stephen Rauch
1,53751129
1,53751129
asked Feb 26 '18 at 2:05
powderpowder
1011
asked Feb 26 '18 at 2:05
powderpowder
1011
asked Feb 26 '18 at 2:05
powderpowder
1011
1011
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
The task is denoising, so I think you can go with many-to-one mapping between distribution, and then I would probably try changes in generatr architecture if it won't learn properly.
With multiple models, you'd have to classify the type of noise to select correct trained model for particular noise distribution.
And about the CycleGAN...
CycleGAN is for unpaired images. It tries to learn generally more complex problem, because it does not require paired images.
Since you have paired images, you should utilize that fact and go for pix2pix which needs paired images. Also, CycleGAN mas 2 generators and 2 discriminators, so you have bigger model and thus you need more computational power.
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f28294%2fgenerative-adversarial-networks-for-multiple-distribution-noise-removal%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
The task is denoising, so I think you can go with many-to-one mapping between distribution, and then I would probably try changes in generatr architecture if it won't learn properly.
With multiple models, you'd have to classify the type of noise to select correct trained model for particular noise distribution.
And about the CycleGAN...
CycleGAN is for unpaired images. It tries to learn generally more complex problem, because it does not require paired images.
Since you have paired images, you should utilize that fact and go for pix2pix which needs paired images. Also, CycleGAN mas 2 generators and 2 discriminators, so you have bigger model and thus you need more computational power.
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
The task is denoising, so I think you can go with many-to-one mapping between distribution, and then I would probably try changes in generatr architecture if it won't learn properly.
With multiple models, you'd have to classify the type of noise to select correct trained model for particular noise distribution.
And about the CycleGAN...
CycleGAN is for unpaired images. It tries to learn generally more complex problem, because it does not require paired images.
Since you have paired images, you should utilize that fact and go for pix2pix which needs paired images. Also, CycleGAN mas 2 generators and 2 discriminators, so you have bigger model and thus you need more computational power.
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
The task is denoising, so I think you can go with many-to-one mapping between distribution, and then I would probably try changes in generatr architecture if it won't learn properly.
With multiple models, you'd have to classify the type of noise to select correct trained model for particular noise distribution.
And about the CycleGAN...
CycleGAN is for unpaired images. It tries to learn generally more complex problem, because it does not require paired images.
Since you have paired images, you should utilize that fact and go for pix2pix which needs paired images. Also, CycleGAN mas 2 generators and 2 discriminators, so you have bigger model and thus you need more computational power.
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
The task is denoising, so I think you can go with many-to-one mapping between distribution, and then I would probably try changes in generatr architecture if it won't learn properly.
With multiple models, you'd have to classify the type of noise to select correct trained model for particular noise distribution.
And about the CycleGAN...
CycleGAN is for unpaired images. It tries to learn generally more complex problem, because it does not require paired images.
Since you have paired images, you should utilize that fact and go for pix2pix which needs paired images. Also, CycleGAN mas 2 generators and 2 discriminators, so you have bigger model and thus you need more computational power.
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
answered 4 hours ago
Matěj RačinskýMatěj Račinský
101
101
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Matěj Račinský is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f28294%2fgenerative-adversarial-networks-for-multiple-distribution-noise-removal%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
