{
  "fetched_at": "2026-10-24T03:09:25Z",
  "source_url": "https://www.kaggle.com/competitions/cvdl2020bird/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set annotation</li>\n<li><strong>valid.csv</strong> - the validation set annotation</li>\n<li><strong>train.zip</strong> - the test set</li>\n<li><strong>valid.zip</strong> - the validation set</li>\n<li><strong>test.zip</strong> - the test set</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>ID</strong> Image ID, 5bits</li>\n<li><strong>Category</strong> Image Category, 0~179 for 180 categories</li>\n</ul",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Fine-grained classification is a classical task in Computer Vision(CV). The task is to specify the fine-grained category of an object. For example, youe may need to figure out the brand of a car or the name of a bird. In this task, we provide a dataset of 180 bird species. 24497 training images, 900 test images(5 per species) and 900 validation images(5 per species). All images are 224 X 224 X 3 color images in jpg format.\n\nParticipants should train their own models using ONLY the training data, and any format of extra data is not allowed. For online evaluation, evaluate your model on the testing data, and record the predictions in a separate .csv file with the same format of train.csv, then upload to the submission page. NOTE that the public leaderboard only shows the accuracy over a subset of the testing set, and the final ranking is based on another subset and is only kept private until the competition ends.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:</p>\r\n<hr />\r\n<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\r\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\r\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\r\n<h2>Submission Format</h2>\r\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).</p>\r\n<p>The file should contain a header and have the following format:</p>\r\n<pre>AuthorId,DuplicateAuthorIds<br />1,1<br /><span style=\"font-size: 14px; line-height: 1.4em;\">8,8<br />9,9 10<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">10,10 9<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}