Hfrxdjt

How old can references or sources in a thesis be?

Dragon forelimb placement

What's the point of deactivating Num Lock on login screens?

How to format long polynomial?

Risk of getting Chronic Wasting Disease (CWD) in the United States?

Python: next in for loop

Why "Having chlorophyll without photosynthesis is actually very dangerous" and "like living with a bomb"?

What do the dots in this tr command do: tr .............A-Z A-ZA-Z <<< "JVPQBOV" (with 13 dots)

How to write a macro that is braces sensitive?

The Two and the One

Which models of the Boeing 737 are still in production?

Why are electrically insulating heatsinks so rare? Is it just cost?

In Japanese, what’s the difference between “Tonari ni” (となりに) and “Tsugi” (つぎ)? When would you use one over the other?

"You are your self first supporter", a more proper way to say it

How can I prevent hyper evolved versions of regular creatures from wiping out their cousins?

Is it possible to do 50 km distance without any previous training?

Why doesn't Newton's third law mean a person bounces back to where they started when they hit the ground?

Can divisibility rules for digits be generalized to sum of digits

can i play a electric guitar through a bass amp?

"to be prejudice towards/against someone" vs "to be prejudiced against/towards someone"

Do VLANs within a subnet need to have their own subnet for router on a stick?

Is it tax fraud for an individual to declare non-taxable revenue as taxable income? (US tax laws)

Has the BBC provided arguments for saying Brexit being cancelled is unlikely?

What is the word for reserving something for yourself before others do?

What does the embedding mean in the FaceNet?

2

$begingroup$

I am reading the paper about FaceNet but I can't get what does the embedding mean in this paper? Is it a hidden layer of the deep CNN?
P.S. English isn't my native language.

cnn embeddings

share|improve this question

asked Nov 13 '18 at 22:50

ШахШах

1257

$endgroup$

add a comment | 

2

$begingroup$

I am reading the paper about FaceNet but I can't get what does the embedding mean in this paper? Is it a hidden layer of the deep CNN?
P.S. English isn't my native language.

cnn embeddings

share|improve this question

asked Nov 13 '18 at 22:50

ШахШах

1257

$endgroup$

add a comment | 

$begingroup$

I am reading the paper about FaceNet but I can't get what does the embedding mean in this paper? Is it a hidden layer of the deep CNN?
P.S. English isn't my native language.

cnn embeddings

share|improve this question

asked Nov 13 '18 at 22:50

ШахШах

1257

$endgroup$

share|improve this question

asked Nov 13 '18 at 22:50

ШахШах

1257

share|improve this question

asked Nov 13 '18 at 22:50

ШахШах

1257

asked Nov 13 '18 at 22:50

ШахШах

1257

asked Nov 13 '18 at 22:50

ШахШах

1257

2 Answers
2

active

oldest

votes

2

$begingroup$

Assume you have features wich lie in a $R^n$ space, e.g. your input is a picture with $28 times 28$ pixels, then $n$ would be $28 times 28 = 784$.

Now you can "embedd" your features into another $R^d$ space, where often $d < n$. This way you learn a rich representation of your input. When you compress your $784$ input-pixels to, lets say $64$ you compressed your input by more than a factor $10$ and can elimnate redundant/useless features.

This embedding learning is of course done in such a way, that you could fully restore your original $784$ pixels out of your $64$ compressed pixels.

share|improve this answer

edited Nov 15 '18 at 9:32

answered Nov 14 '18 at 8:13

Andreas LookAndreas Look

431110

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for simple and clear explanation, seems I could get it!
  $endgroup$
  – Шах
  Nov 14 '18 at 20:52
  

  
  
  
  

add a comment | 

2

$begingroup$

An embedding is a mapping from discrete objects, such as words, to vectors of real numbers.

- Tensorflow/Embeddings

With reference to the FaceNet paper, I should say that embedding here simply means the tensor obtained by performing a forward propagation over an image. The obtained embedding of the image and the target image are then compared to find the closeness among the images. The loss function specified by the equation $L=sum_i^N [ ||f(x_i^a)-f(x_i^p)||_2^2-||f(x_i^a)-f(x_i^n)||_2^2+alpha]_+ $ is simply used here to to find the euclidean distance between the generated embedding of the anchor, positive and negative images obtained by performing forward propagation. This technique is also called as Siamese network.

I suggest you to read the full original FaceNet paper for clearer understanding of the FaceNet architecture and working.

share|improve this answer

edited 44 mins ago

answered Nov 14 '18 at 20:23

thanatozthanatoz

569319

$endgroup$

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
);



);

draft saved

draft discarded

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

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f41185%2fwhat-does-the-embedding-mean-in-the-facenet%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

2

$begingroup$

Assume you have features wich lie in a $R^n$ space, e.g. your input is a picture with $28 times 28$ pixels, then $n$ would be $28 times 28 = 784$.

Now you can "embedd" your features into another $R^d$ space, where often $d < n$. This way you learn a rich representation of your input. When you compress your $784$ input-pixels to, lets say $64$ you compressed your input by more than a factor $10$ and can elimnate redundant/useless features.

This embedding learning is of course done in such a way, that you could fully restore your original $784$ pixels out of your $64$ compressed pixels.

share|improve this answer

edited Nov 15 '18 at 9:32

answered Nov 14 '18 at 8:13

Andreas LookAndreas Look

431110

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for simple and clear explanation, seems I could get it!
  $endgroup$
  – Шах
  Nov 14 '18 at 20:52
  

  
  
  
  

add a comment | 

2

$begingroup$

Assume you have features wich lie in a $R^n$ space, e.g. your input is a picture with $28 times 28$ pixels, then $n$ would be $28 times 28 = 784$.

Now you can "embedd" your features into another $R^d$ space, where often $d < n$. This way you learn a rich representation of your input. When you compress your $784$ input-pixels to, lets say $64$ you compressed your input by more than a factor $10$ and can elimnate redundant/useless features.

This embedding learning is of course done in such a way, that you could fully restore your original $784$ pixels out of your $64$ compressed pixels.

share|improve this answer

edited Nov 15 '18 at 9:32

answered Nov 14 '18 at 8:13

Andreas LookAndreas Look

431110

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for simple and clear explanation, seems I could get it!
  $endgroup$
  – Шах
  Nov 14 '18 at 20:52
  

  
  
  
  

add a comment | 

$begingroup$

Assume you have features wich lie in a $R^n$ space, e.g. your input is a picture with $28 times 28$ pixels, then $n$ would be $28 times 28 = 784$.

Now you can "embedd" your features into another $R^d$ space, where often $d < n$. This way you learn a rich representation of your input. When you compress your $784$ input-pixels to, lets say $64$ you compressed your input by more than a factor $10$ and can elimnate redundant/useless features.

This embedding learning is of course done in such a way, that you could fully restore your original $784$ pixels out of your $64$ compressed pixels.

share|improve this answer

edited Nov 15 '18 at 9:32

answered Nov 14 '18 at 8:13

Andreas LookAndreas Look

431110

$endgroup$

share|improve this answer

edited Nov 15 '18 at 9:32

answered Nov 14 '18 at 8:13

Andreas LookAndreas Look

431110

answered Nov 14 '18 at 8:13

Andreas LookAndreas Look

431110

answered Nov 14 '18 at 8:13

Andreas LookAndreas Look

431110

2

$begingroup$

An embedding is a mapping from discrete objects, such as words, to vectors of real numbers.

- Tensorflow/Embeddings

With reference to the FaceNet paper, I should say that embedding here simply means the tensor obtained by performing a forward propagation over an image. The obtained embedding of the image and the target image are then compared to find the closeness among the images. The loss function specified by the equation $L=sum_i^N [ ||f(x_i^a)-f(x_i^p)||_2^2-||f(x_i^a)-f(x_i^n)||_2^2+alpha]_+ $ is simply used here to to find the euclidean distance between the generated embedding of the anchor, positive and negative images obtained by performing forward propagation. This technique is also called as Siamese network.

I suggest you to read the full original FaceNet paper for clearer understanding of the FaceNet architecture and working.

share|improve this answer

edited 44 mins ago

answered Nov 14 '18 at 20:23

thanatozthanatoz

569319

$endgroup$

add a comment | 

2

$begingroup$

An embedding is a mapping from discrete objects, such as words, to vectors of real numbers.

- Tensorflow/Embeddings

With reference to the FaceNet paper, I should say that embedding here simply means the tensor obtained by performing a forward propagation over an image. The obtained embedding of the image and the target image are then compared to find the closeness among the images. The loss function specified by the equation $L=sum_i^N [ ||f(x_i^a)-f(x_i^p)||_2^2-||f(x_i^a)-f(x_i^n)||_2^2+alpha]_+ $ is simply used here to to find the euclidean distance between the generated embedding of the anchor, positive and negative images obtained by performing forward propagation. This technique is also called as Siamese network.

I suggest you to read the full original FaceNet paper for clearer understanding of the FaceNet architecture and working.

share|improve this answer

edited 44 mins ago

answered Nov 14 '18 at 20:23

thanatozthanatoz

569319

$endgroup$

add a comment | 

$begingroup$

An embedding is a mapping from discrete objects, such as words, to vectors of real numbers.

- Tensorflow/Embeddings

With reference to the FaceNet paper, I should say that embedding here simply means the tensor obtained by performing a forward propagation over an image. The obtained embedding of the image and the target image are then compared to find the closeness among the images. The loss function specified by the equation $L=sum_i^N [ ||f(x_i^a)-f(x_i^p)||_2^2-||f(x_i^a)-f(x_i^n)||_2^2+alpha]_+ $ is simply used here to to find the euclidean distance between the generated embedding of the anchor, positive and negative images obtained by performing forward propagation. This technique is also called as Siamese network.

I suggest you to read the full original FaceNet paper for clearer understanding of the FaceNet architecture and working.

share|improve this answer

edited 44 mins ago

answered Nov 14 '18 at 20:23

thanatozthanatoz

569319

$endgroup$

share|improve this answer

edited 44 mins ago

answered Nov 14 '18 at 20:23

thanatozthanatoz

569319

answered Nov 14 '18 at 20:23

thanatozthanatoz

569319

answered Nov 14 '18 at 20:23

thanatozthanatoz

569319