Learning image embddings for clustering based on custom distance metric












1












$begingroup$


I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.



I found this on here




Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that




But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.



I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!










share|improve this question







New contributor




kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    1












    $begingroup$


    I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.



    I found this on here




    Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that




    But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.



    I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!










    share|improve this question







    New contributor




    kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      1












      1








      1





      $begingroup$


      I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.



      I found this on here




      Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that




      But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.



      I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!










      share|improve this question







      New contributor




      kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(or anyone else for that matter). My idea was to cluster these images, and then infer similar features for the new images, as those in the same cluster. I tried using the vgg16, vgg19, and resnet50 to encode the images and then use DBSCAN to cluster. It worked decently, however from my experience, DBSCAN does not work optimally in such a high dimensional space.



      I found this on here




      Another way is to learn an embedding that optimizes your similarity metric using a neural network and just cluster that




      But i am not sure what is meant here, how exactly should i train the network, in my mind i would have to define a loss function that punishes bad encodings. I though of simply taking the square distance between the calculated distance, and the distance in the encoded space, however i feel like there are multiple issues with that.



      I am most comfortable with keras, so if anybody know a repo or something along those lines, i would be grateful aswell!







      python neural-network deep-learning image-recognition






      share|improve this question







      New contributor




      kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question







      New contributor




      kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question






      New contributor




      kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked 2 days ago









      kumalkakumalka

      61




      61




      New contributor




      kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      kumalka is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          0






          active

          oldest

          votes











          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
          });


          }
          });






          kumalka is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47234%2flearning-image-embddings-for-clustering-based-on-custom-distance-metric%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          kumalka is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          kumalka is a new contributor. Be nice, and check out our Code of Conduct.













          kumalka is a new contributor. Be nice, and check out our Code of Conduct.












          kumalka is a new contributor. Be nice, and check out our Code of Conduct.
















          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%2f47234%2flearning-image-embddings-for-clustering-based-on-custom-distance-metric%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