Image Segmentation - binary cross entropy indicates over-fitting, dice doesn't









up vote
-1
down vote

favorite












I encountered a problem which is difficult for me to explain:



enter image description here
I train a modified UNet variant with binary cross entropy and I plot the dice scores as well. This is how the result looks like. The distribution of the mask pixels in the training and the test set are different.



Can anyone elaborate why dice and BCE is not correlating at all in this case? Or what are potential reasons why the two are not correlating?



Thanks!










share|improve this question

























    up vote
    -1
    down vote

    favorite












    I encountered a problem which is difficult for me to explain:



    enter image description here
    I train a modified UNet variant with binary cross entropy and I plot the dice scores as well. This is how the result looks like. The distribution of the mask pixels in the training and the test set are different.



    Can anyone elaborate why dice and BCE is not correlating at all in this case? Or what are potential reasons why the two are not correlating?



    Thanks!










    share|improve this question























      up vote
      -1
      down vote

      favorite









      up vote
      -1
      down vote

      favorite











      I encountered a problem which is difficult for me to explain:



      enter image description here
      I train a modified UNet variant with binary cross entropy and I plot the dice scores as well. This is how the result looks like. The distribution of the mask pixels in the training and the test set are different.



      Can anyone elaborate why dice and BCE is not correlating at all in this case? Or what are potential reasons why the two are not correlating?



      Thanks!










      share|improve this question













      I encountered a problem which is difficult for me to explain:



      enter image description here
      I train a modified UNet variant with binary cross entropy and I plot the dice scores as well. This is how the result looks like. The distribution of the mask pixels in the training and the test set are different.



      Can anyone elaborate why dice and BCE is not correlating at all in this case? Or what are potential reasons why the two are not correlating?



      Thanks!







      deep-learning






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 11 at 14:54









      Styp

      1398




      1398



























          active

          oldest

          votes











          Your Answer






          StackExchange.ifUsing("editor", function ()
          StackExchange.using("externalEditor", function ()
          StackExchange.using("snippets", function ()
          StackExchange.snippets.init();
          );
          );
          , "code-snippets");

          StackExchange.ready(function()
          var channelOptions =
          tags: "".split(" "),
          id: "1"
          ;
          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',
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          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%2fstackoverflow.com%2fquestions%2f53249926%2fimage-segmentation-binary-cross-entropy-indicates-over-fitting-dice-doesnt%23new-answer', 'question_page');

          );

          Post as a guest















          Required, but never shown






























          active

          oldest

          votes













          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes















          draft saved

          draft discarded
















































          Thanks for contributing an answer to Stack Overflow!


          • 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.

          To learn more, see our tips on writing great answers.





          Some of your past answers have not been well-received, and you're in danger of being blocked from answering.


          Please pay close attention to the following guidance:


          • 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.

          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%2fstackoverflow.com%2fquestions%2f53249926%2fimage-segmentation-binary-cross-entropy-indicates-over-fitting-dice-doesnt%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

          Top Tejano songwriter Luis Silva dead of heart attack at 64

          政党

          天津地下鉄3号線