What is Coarse-to-Fine in the context of neural networks? The Next CEO of Stack Overflow2019 Community Moderator ElectionWhat is the “dying ReLU” problem in neural networks?Unable to figure out the linear embedding layer in the convolutional neural network?Is the graphic of deep residual networks wrong?Why is video classification still not that accurate?Transforming the input data for neural networksWhat is the difference between Dilated Convolution and Deconvolution?Gradient ExchangeWords as features of a neural networksEncoder Decoder networks with varying image sizesConjugated gradient method. What is an A-matrix in case of neural networks
Why did the Drakh emissary look so blurred in S04:E11 "Lines of Communication"?
Can this transistor (2N2222) take 6 V on emitter-base? Am I reading the datasheet incorrectly?
Oldie but Goldie
What is the difference between 서고 and 도서관?
Find a path from s to t using as few red nodes as possible
Incomplete cube
Can a PhD from a non-TU9 German university become a professor in a TU9 university?
Creating a script with console commands
How dangerous is XSS
Can you teleport closer to a creature you are Frightened of?
How exploitable/balanced is this homebrew spell: Spell Permanency?
What happens if you break a law in another country outside of that country?
Is this a new Fibonacci Identity?
Which acid/base does a strong base/acid react when added to a buffer solution?
That's an odd coin - I wonder why
Mathematica command that allows it to read my intentions
Planeswalker Ability and Death Timing
pgfplots: How to draw a tangent graph below two others?
Identify and count spells (Distinctive events within each group)
Advance Calculus Limit question
Does int main() need a declaration on C++?
Car headlights in a world without electricity
My boss doesn't want me to have a side project
Prodigo = pro + ago?
What is Coarse-to-Fine in the context of neural networks?
The Next CEO of Stack Overflow2019 Community Moderator ElectionWhat is the “dying ReLU” problem in neural networks?Unable to figure out the linear embedding layer in the convolutional neural network?Is the graphic of deep residual networks wrong?Why is video classification still not that accurate?Transforming the input data for neural networksWhat is the difference between Dilated Convolution and Deconvolution?Gradient ExchangeWords as features of a neural networksEncoder Decoder networks with varying image sizesConjugated gradient method. What is an A-matrix in case of neural networks
$begingroup$
I read in many paper that mentions coarse-to-fine as a technique in deep learning, but I could never figure what exactly they mean. Is it related to multiscale inference, where they use coarse and fine input images?
neural-network deep-learning computer-vision
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
$endgroup$
add a comment |
$begingroup$
I read in many paper that mentions coarse-to-fine as a technique in deep learning, but I could never figure what exactly they mean. Is it related to multiscale inference, where they use coarse and fine input images?
neural-network deep-learning computer-vision
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
$endgroup$
1
$begingroup$
This question is probably incomplete , was part of it lost in copy/paste ?
$endgroup$
– Shamit Verma
Mar 25 at 6:56
$begingroup$
Opps I don't know what happened. Completing it now.
$endgroup$
– Mong H. Ng
Mar 26 at 7:14
add a comment |
$begingroup$
I read in many paper that mentions coarse-to-fine as a technique in deep learning, but I could never figure what exactly they mean. Is it related to multiscale inference, where they use coarse and fine input images?
neural-network deep-learning computer-vision
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
$endgroup$
I read in many paper that mentions coarse-to-fine as a technique in deep learning, but I could never figure what exactly they mean. Is it related to multiscale inference, where they use coarse and fine input images?
neural-network deep-learning computer-vision
neural-network deep-learning computer-vision
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
edited Mar 26 at 7:15
Mong H. Ng
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
asked Mar 25 at 5:52
Mong H. NgMong H. Ng
62
62
1
$begingroup$
This question is probably incomplete , was part of it lost in copy/paste ?
$endgroup$
– Shamit Verma
Mar 25 at 6:56
$begingroup$
Opps I don't know what happened. Completing it now.
$endgroup$
– Mong H. Ng
Mar 26 at 7:14
add a comment |
1
$begingroup$
This question is probably incomplete , was part of it lost in copy/paste ?
$endgroup$
– Shamit Verma
Mar 25 at 6:56
$begingroup$
Opps I don't know what happened. Completing it now.
$endgroup$
– Mong H. Ng
Mar 26 at 7:14
1
1
$begingroup$
This question is probably incomplete , was part of it lost in copy/paste ?
$endgroup$
– Shamit Verma
Mar 25 at 6:56
$begingroup$
This question is probably incomplete , was part of it lost in copy/paste ?
$endgroup$
– Shamit Verma
Mar 25 at 6:56
$begingroup$
Opps I don't know what happened. Completing it now.
$endgroup$
– Mong H. Ng
Mar 26 at 7:14
$begingroup$
Opps I don't know what happened. Completing it now.
$endgroup$
– Mong H. Ng
Mar 26 at 7:14
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
"Coarse to Fine" usually refers to the hyperparameter optimization of a neural network during which you would like to try out different combinations of the hyperparameters and evaluate the performance of the network.
However, due to the large number of parameters AND the big range of their values, it is almost impossible to check all the available combinations. For that reason, you usually discretize the available value range of each parameter into a "coarse" grid of values (i.e. val = 5,6,7,8,9) to estimate the effect of increasing or decreasing the value of that parameter. After selecting the value that seems most promising/meaningful (i.e. val = 6), you perform a "finer" search around it (i.e. val = 5.8, 5.9, 6.0, 6.1, 6.2) to optimize even further.
answered Mar 25 at 7:53
pcko1pcko1
1,611418
$endgroup$
$begingroup$
That's a good answer for the amount of information given. Since he was talking about images there are some methods that train multiple regressors for coarse-to-fine detection of objects. I find this a lot in facial landmark detection. So coarse-to-fine might mean: - Oposite to exhaustive grid search or - Oposite to one shot-detector / yolo
$endgroup$
– Pedro Henrique Monforte
Mar 26 at 11:31
add a comment |
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%2f47921%2fwhat-is-coarse-to-fine-in-the-context-of-neural-networks%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
$begingroup$
"Coarse to Fine" usually refers to the hyperparameter optimization of a neural network during which you would like to try out different combinations of the hyperparameters and evaluate the performance of the network.
However, due to the large number of parameters AND the big range of their values, it is almost impossible to check all the available combinations. For that reason, you usually discretize the available value range of each parameter into a "coarse" grid of values (i.e. val = 5,6,7,8,9) to estimate the effect of increasing or decreasing the value of that parameter. After selecting the value that seems most promising/meaningful (i.e. val = 6), you perform a "finer" search around it (i.e. val = 5.8, 5.9, 6.0, 6.1, 6.2) to optimize even further.
answered Mar 25 at 7:53
pcko1pcko1
1,611418
$endgroup$
$begingroup$
That's a good answer for the amount of information given. Since he was talking about images there are some methods that train multiple regressors for coarse-to-fine detection of objects. I find this a lot in facial landmark detection. So coarse-to-fine might mean: - Oposite to exhaustive grid search or - Oposite to one shot-detector / yolo
$endgroup$
– Pedro Henrique Monforte
Mar 26 at 11:31
add a comment |
$begingroup$
"Coarse to Fine" usually refers to the hyperparameter optimization of a neural network during which you would like to try out different combinations of the hyperparameters and evaluate the performance of the network.
However, due to the large number of parameters AND the big range of their values, it is almost impossible to check all the available combinations. For that reason, you usually discretize the available value range of each parameter into a "coarse" grid of values (i.e. val = 5,6,7,8,9) to estimate the effect of increasing or decreasing the value of that parameter. After selecting the value that seems most promising/meaningful (i.e. val = 6), you perform a "finer" search around it (i.e. val = 5.8, 5.9, 6.0, 6.1, 6.2) to optimize even further.
answered Mar 25 at 7:53
pcko1pcko1
1,611418
$endgroup$
$begingroup$
That's a good answer for the amount of information given. Since he was talking about images there are some methods that train multiple regressors for coarse-to-fine detection of objects. I find this a lot in facial landmark detection. So coarse-to-fine might mean: - Oposite to exhaustive grid search or - Oposite to one shot-detector / yolo
$endgroup$
– Pedro Henrique Monforte
Mar 26 at 11:31
add a comment |
$begingroup$
"Coarse to Fine" usually refers to the hyperparameter optimization of a neural network during which you would like to try out different combinations of the hyperparameters and evaluate the performance of the network.
However, due to the large number of parameters AND the big range of their values, it is almost impossible to check all the available combinations. For that reason, you usually discretize the available value range of each parameter into a "coarse" grid of values (i.e. val = 5,6,7,8,9) to estimate the effect of increasing or decreasing the value of that parameter. After selecting the value that seems most promising/meaningful (i.e. val = 6), you perform a "finer" search around it (i.e. val = 5.8, 5.9, 6.0, 6.1, 6.2) to optimize even further.
answered Mar 25 at 7:53
pcko1pcko1
1,611418
$endgroup$
"Coarse to Fine" usually refers to the hyperparameter optimization of a neural network during which you would like to try out different combinations of the hyperparameters and evaluate the performance of the network.
However, due to the large number of parameters AND the big range of their values, it is almost impossible to check all the available combinations. For that reason, you usually discretize the available value range of each parameter into a "coarse" grid of values (i.e. val = 5,6,7,8,9) to estimate the effect of increasing or decreasing the value of that parameter. After selecting the value that seems most promising/meaningful (i.e. val = 6), you perform a "finer" search around it (i.e. val = 5.8, 5.9, 6.0, 6.1, 6.2) to optimize even further.
answered Mar 25 at 7:53
pcko1pcko1
1,611418
answered Mar 25 at 7:53
pcko1pcko1
1,611418
answered Mar 25 at 7:53
pcko1pcko1
1,611418
answered Mar 25 at 7:53
pcko1pcko1
1,611418
1,611418
$begingroup$
That's a good answer for the amount of information given. Since he was talking about images there are some methods that train multiple regressors for coarse-to-fine detection of objects. I find this a lot in facial landmark detection. So coarse-to-fine might mean: - Oposite to exhaustive grid search or - Oposite to one shot-detector / yolo
$endgroup$
– Pedro Henrique Monforte
Mar 26 at 11:31
add a comment |
$begingroup$
That's a good answer for the amount of information given. Since he was talking about images there are some methods that train multiple regressors for coarse-to-fine detection of objects. I find this a lot in facial landmark detection. So coarse-to-fine might mean: - Oposite to exhaustive grid search or - Oposite to one shot-detector / yolo
$endgroup$
– Pedro Henrique Monforte
Mar 26 at 11:31
$begingroup$
That's a good answer for the amount of information given. Since he was talking about images there are some methods that train multiple regressors for coarse-to-fine detection of objects. I find this a lot in facial landmark detection. So coarse-to-fine might mean: - Oposite to exhaustive grid search or - Oposite to one shot-detector / yolo
$endgroup$
– Pedro Henrique Monforte
Mar 26 at 11:31
$begingroup$
That's a good answer for the amount of information given. Since he was talking about images there are some methods that train multiple regressors for coarse-to-fine detection of objects. I find this a lot in facial landmark detection. So coarse-to-fine might mean: - Oposite to exhaustive grid search or - Oposite to one shot-detector / yolo
$endgroup$
– Pedro Henrique Monforte
Mar 26 at 11:31
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%2f47921%2fwhat-is-coarse-to-fine-in-the-context-of-neural-networks%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
1
$begingroup$
This question is probably incomplete , was part of it lost in copy/paste ?
$endgroup$
– Shamit Verma
Mar 25 at 6:56
$begingroup$
Opps I don't know what happened. Completing it now.
$endgroup$
– Mong H. Ng
Mar 26 at 7:14