Unable to figure out the linear embedding layer in the convolutional neural network?












12












$begingroup$


I have the network architecture from the paper "learning fine-grained image similarity with deep ranking" and I am unable to figure out how the output from the three parallel network is merged using the linear embedding layer.
The only information given on this layer, in the paper is




Finally, we normalize the embeddings from the three parts, and combine them with a linear embedding layer. The dimension of the embedding is 4096.




Can anyone help me in figuring out what exactly does the author mean when he is talking about this layer?










share|improve this question











$endgroup$




bumped to the homepage by Community 10 hours ago


This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.















  • $begingroup$
    It's unfortunate for me that there is no answer for this question. Because I'm stuck with the exactly same issue. Did you figure it out?
    $endgroup$
    – LKM
    Oct 10 '17 at 16:51










  • $begingroup$
    I did not figure out the answer but i just concatenated the input from the three parts and passed it through a dense layer containing 4096 nodes.
    $endgroup$
    – A. Sam
    Oct 12 '17 at 8:53
















12












$begingroup$


I have the network architecture from the paper "learning fine-grained image similarity with deep ranking" and I am unable to figure out how the output from the three parallel network is merged using the linear embedding layer.
The only information given on this layer, in the paper is




Finally, we normalize the embeddings from the three parts, and combine them with a linear embedding layer. The dimension of the embedding is 4096.




Can anyone help me in figuring out what exactly does the author mean when he is talking about this layer?










share|improve this question











$endgroup$




bumped to the homepage by Community 10 hours ago


This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.















  • $begingroup$
    It's unfortunate for me that there is no answer for this question. Because I'm stuck with the exactly same issue. Did you figure it out?
    $endgroup$
    – LKM
    Oct 10 '17 at 16:51










  • $begingroup$
    I did not figure out the answer but i just concatenated the input from the three parts and passed it through a dense layer containing 4096 nodes.
    $endgroup$
    – A. Sam
    Oct 12 '17 at 8:53














12












12








12





$begingroup$


I have the network architecture from the paper "learning fine-grained image similarity with deep ranking" and I am unable to figure out how the output from the three parallel network is merged using the linear embedding layer.
The only information given on this layer, in the paper is




Finally, we normalize the embeddings from the three parts, and combine them with a linear embedding layer. The dimension of the embedding is 4096.




Can anyone help me in figuring out what exactly does the author mean when he is talking about this layer?










share|improve this question











$endgroup$




I have the network architecture from the paper "learning fine-grained image similarity with deep ranking" and I am unable to figure out how the output from the three parallel network is merged using the linear embedding layer.
The only information given on this layer, in the paper is




Finally, we normalize the embeddings from the three parts, and combine them with a linear embedding layer. The dimension of the embedding is 4096.




Can anyone help me in figuring out what exactly does the author mean when he is talking about this layer?







neural-network deep-network






share|improve this question















share|improve this question













share|improve this question




share|improve this question








edited Nov 23 '18 at 12:25









Snympi

132114




132114










asked Oct 7 '16 at 6:16









A. SamA. Sam

1685




1685





bumped to the homepage by Community 10 hours ago


This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.







bumped to the homepage by Community 10 hours ago


This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.














  • $begingroup$
    It's unfortunate for me that there is no answer for this question. Because I'm stuck with the exactly same issue. Did you figure it out?
    $endgroup$
    – LKM
    Oct 10 '17 at 16:51










  • $begingroup$
    I did not figure out the answer but i just concatenated the input from the three parts and passed it through a dense layer containing 4096 nodes.
    $endgroup$
    – A. Sam
    Oct 12 '17 at 8:53


















  • $begingroup$
    It's unfortunate for me that there is no answer for this question. Because I'm stuck with the exactly same issue. Did you figure it out?
    $endgroup$
    – LKM
    Oct 10 '17 at 16:51










  • $begingroup$
    I did not figure out the answer but i just concatenated the input from the three parts and passed it through a dense layer containing 4096 nodes.
    $endgroup$
    – A. Sam
    Oct 12 '17 at 8:53
















$begingroup$
It's unfortunate for me that there is no answer for this question. Because I'm stuck with the exactly same issue. Did you figure it out?
$endgroup$
– LKM
Oct 10 '17 at 16:51




$begingroup$
It's unfortunate for me that there is no answer for this question. Because I'm stuck with the exactly same issue. Did you figure it out?
$endgroup$
– LKM
Oct 10 '17 at 16:51












$begingroup$
I did not figure out the answer but i just concatenated the input from the three parts and passed it through a dense layer containing 4096 nodes.
$endgroup$
– A. Sam
Oct 12 '17 at 8:53




$begingroup$
I did not figure out the answer but i just concatenated the input from the three parts and passed it through a dense layer containing 4096 nodes.
$endgroup$
– A. Sam
Oct 12 '17 at 8:53










2 Answers
2






active

oldest

votes


















0












$begingroup$

It's mentioned in the paper:




A local normalization layer normalizes the feature map
around a local neighborhood to have unit norm and zero
mean. It leads to feature maps that are robust to the differences
in illumination and contrast.




They take each part of the model and normalize it separately.



As for combining them, as you commented, to capture the most salient features, with under-complete representation no needs for the non-linearity.






share|improve this answer









$endgroup$





















    0












    $begingroup$

    Linear embedding layer must be just a fancy name for a dense layer with no activation.
    'Linear' means there is no activation (activation is identity). And the embedding is rather a concept for a vector representation of the input data (e.g. word embeddings). I believe the elements from the second vector are simply added to the first one element-wise.






    share|improve this answer









    $endgroup$













      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%2f14412%2funable-to-figure-out-the-linear-embedding-layer-in-the-convolutional-neural-netw%23new-answer', 'question_page');
      }
      );

      Post as a guest















      Required, but never shown

























      2 Answers
      2






      active

      oldest

      votes








      2 Answers
      2






      active

      oldest

      votes









      active

      oldest

      votes






      active

      oldest

      votes









      0












      $begingroup$

      It's mentioned in the paper:




      A local normalization layer normalizes the feature map
      around a local neighborhood to have unit norm and zero
      mean. It leads to feature maps that are robust to the differences
      in illumination and contrast.




      They take each part of the model and normalize it separately.



      As for combining them, as you commented, to capture the most salient features, with under-complete representation no needs for the non-linearity.






      share|improve this answer









      $endgroup$


















        0












        $begingroup$

        It's mentioned in the paper:




        A local normalization layer normalizes the feature map
        around a local neighborhood to have unit norm and zero
        mean. It leads to feature maps that are robust to the differences
        in illumination and contrast.




        They take each part of the model and normalize it separately.



        As for combining them, as you commented, to capture the most salient features, with under-complete representation no needs for the non-linearity.






        share|improve this answer









        $endgroup$
















          0












          0








          0





          $begingroup$

          It's mentioned in the paper:




          A local normalization layer normalizes the feature map
          around a local neighborhood to have unit norm and zero
          mean. It leads to feature maps that are robust to the differences
          in illumination and contrast.




          They take each part of the model and normalize it separately.



          As for combining them, as you commented, to capture the most salient features, with under-complete representation no needs for the non-linearity.






          share|improve this answer









          $endgroup$



          It's mentioned in the paper:




          A local normalization layer normalizes the feature map
          around a local neighborhood to have unit norm and zero
          mean. It leads to feature maps that are robust to the differences
          in illumination and contrast.




          They take each part of the model and normalize it separately.



          As for combining them, as you commented, to capture the most salient features, with under-complete representation no needs for the non-linearity.







          share|improve this answer












          share|improve this answer



          share|improve this answer










          answered May 7 '18 at 5:17









          Fadi BakouraFadi Bakoura

          653111




          653111























              0












              $begingroup$

              Linear embedding layer must be just a fancy name for a dense layer with no activation.
              'Linear' means there is no activation (activation is identity). And the embedding is rather a concept for a vector representation of the input data (e.g. word embeddings). I believe the elements from the second vector are simply added to the first one element-wise.






              share|improve this answer









              $endgroup$


















                0












                $begingroup$

                Linear embedding layer must be just a fancy name for a dense layer with no activation.
                'Linear' means there is no activation (activation is identity). And the embedding is rather a concept for a vector representation of the input data (e.g. word embeddings). I believe the elements from the second vector are simply added to the first one element-wise.






                share|improve this answer









                $endgroup$
















                  0












                  0








                  0





                  $begingroup$

                  Linear embedding layer must be just a fancy name for a dense layer with no activation.
                  'Linear' means there is no activation (activation is identity). And the embedding is rather a concept for a vector representation of the input data (e.g. word embeddings). I believe the elements from the second vector are simply added to the first one element-wise.






                  share|improve this answer









                  $endgroup$



                  Linear embedding layer must be just a fancy name for a dense layer with no activation.
                  'Linear' means there is no activation (activation is identity). And the embedding is rather a concept for a vector representation of the input data (e.g. word embeddings). I believe the elements from the second vector are simply added to the first one element-wise.







                  share|improve this answer












                  share|improve this answer



                  share|improve this answer










                  answered Jan 11 at 14:45









                  Dmytro PrylipkoDmytro Prylipko

                  4387




                  4387






























                      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%2f14412%2funable-to-figure-out-the-linear-embedding-layer-in-the-convolutional-neural-netw%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

                      How to label and detect the document text images

                      Vallis Paradisi

                      Tabula Rosettana