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 Overflow
2019 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










1












$begingroup$


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?










share|improve this question











$endgroup$







  • 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
















1












$begingroup$


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?










share|improve this question











$endgroup$







  • 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














1












1








1





$begingroup$


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?










share|improve this question











$endgroup$




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






share|improve this question















share|improve this question













share|improve this question




share|improve this question








edited Mar 26 at 7:15







Mong H. Ng

















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













  • 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











1 Answer
1






active

oldest

votes


















1












$begingroup$

"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.






share|improve this answer









$endgroup$












  • $begingroup$
    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











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
);



);













draft saved

draft discarded


















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









1












$begingroup$

"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.






share|improve this answer









$endgroup$












  • $begingroup$
    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















1












$begingroup$

"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.






share|improve this answer









$endgroup$












  • $begingroup$
    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













1












1








1





$begingroup$

"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.






share|improve this answer









$endgroup$



"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.







share|improve this answer












share|improve this answer



share|improve this answer










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
















  • $begingroup$
    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

















draft saved

draft discarded
















































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.




draft saved


draft discarded














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





















































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







Popular posts from this blog

Adding axes to figuresAdding axes labels to LaTeX figuresLaTeX equivalent of ConTeXt buffersRotate a node but not its content: the case of the ellipse decorationHow to define the default vertical distance between nodes?TikZ scaling graphic and adjust node position and keep font sizeNumerical conditional within tikz keys?adding axes to shapesAlign axes across subfiguresAdding figures with a certain orderLine up nested tikz enviroments or how to get rid of themAdding axes labels to LaTeX figures

Tähtien Talli Jäsenet | Lähteet | NavigointivalikkoSuomen Hippos – Tähtien Talli

Do these cracks on my tires look bad? The Next CEO of Stack OverflowDry rot tire should I replace?Having to replace tiresFishtailed so easily? Bad tires? ABS?Filling the tires with something other than air, to avoid puncture hassles?Used Michelin tires safe to install?Do these tyre cracks necessitate replacement?Rumbling noise: tires or mechanicalIs it possible to fix noisy feathered tires?Are bad winter tires still better than summer tires in winter?Torque converter failure - Related to replacing only 2 tires?Why use snow tires on all 4 wheels on 2-wheel-drive cars?