Why not use the anchor boxes for the grid based search to detect objects directly in YOLO algorithm?












0












$begingroup$


The YOLO algorithm does a grid search based on the grid squares (I'm not sure if they ALWAYS are squares) and when an object is detected in one of the squares, check for the maximum 'Intersection over Union' with one of the anchor boxes and then draw the boundary around the object.



My question is, is computational inefficiency the sole reason why we don't simply run these anchor boxes instead of first running the squares around and then checking with the anchor boxes? I am just starting out with this, so I haven't implemented anything of yet. I don't know how costly that inefficiency will be.



Also, why the name 'You Only Look Once'? Is it just the researchers having a fun time or does it have a reason?










share|improve this question









$endgroup$

















    0












    $begingroup$


    The YOLO algorithm does a grid search based on the grid squares (I'm not sure if they ALWAYS are squares) and when an object is detected in one of the squares, check for the maximum 'Intersection over Union' with one of the anchor boxes and then draw the boundary around the object.



    My question is, is computational inefficiency the sole reason why we don't simply run these anchor boxes instead of first running the squares around and then checking with the anchor boxes? I am just starting out with this, so I haven't implemented anything of yet. I don't know how costly that inefficiency will be.



    Also, why the name 'You Only Look Once'? Is it just the researchers having a fun time or does it have a reason?










    share|improve this question









    $endgroup$















      0












      0








      0





      $begingroup$


      The YOLO algorithm does a grid search based on the grid squares (I'm not sure if they ALWAYS are squares) and when an object is detected in one of the squares, check for the maximum 'Intersection over Union' with one of the anchor boxes and then draw the boundary around the object.



      My question is, is computational inefficiency the sole reason why we don't simply run these anchor boxes instead of first running the squares around and then checking with the anchor boxes? I am just starting out with this, so I haven't implemented anything of yet. I don't know how costly that inefficiency will be.



      Also, why the name 'You Only Look Once'? Is it just the researchers having a fun time or does it have a reason?










      share|improve this question









      $endgroup$




      The YOLO algorithm does a grid search based on the grid squares (I'm not sure if they ALWAYS are squares) and when an object is detected in one of the squares, check for the maximum 'Intersection over Union' with one of the anchor boxes and then draw the boundary around the object.



      My question is, is computational inefficiency the sole reason why we don't simply run these anchor boxes instead of first running the squares around and then checking with the anchor boxes? I am just starting out with this, so I haven't implemented anything of yet. I don't know how costly that inefficiency will be.



      Also, why the name 'You Only Look Once'? Is it just the researchers having a fun time or does it have a reason?







      yolo






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked 19 mins ago









      Sakazuki AkainuSakazuki Akainu

      11




      11






















          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
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44271%2fwhy-not-use-the-anchor-boxes-for-the-grid-based-search-to-detect-objects-directl%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
















          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%2f44271%2fwhy-not-use-the-anchor-boxes-for-the-grid-based-search-to-detect-objects-directl%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

          Callistus I

          Tabula Rosettana

          How to label and detect the document text images