{
  "fetched_at": "2026-10-19T17:56:46Z",
  "source_url": "https://www.kaggle.com/competitions/fieldguide-challenge-moths-and-butterflies/data",
  "pages": [
    {
      "name": "rules",
      "content": "<ul>\n<li>ImageNet or iNaturalist pre-trained models are allowed in the competition</li>\n<li>Acquiring additional image/video data is not allowed</li>\n<li>This competition does not count toward Kaggle ranking points or medals</li>\n<li>We ask that you respect the spirit of this competition and do not cheat. Hand-labeling is forbidden.</li>\n<li>One Kaggle account per participant</li>\n<li>No private sharing outside teams</li>\n<li>Participants are allowed to collect additional annotations (e.g. bounding boxes, keypoints) on the provided training and validation sets. Teams should specify that they collected additional annotations when submitting results.</li>\n<li>Team mergers are allowed</li>\n<li>There is no maximum team size</li>\n<li>No distribution of images</li>\n</ul>\n\n<p>Participants should only use the provided training and validation images to train a model to classify the test images. We do not want participants crawling the web in search of additional data for the target categories. Participants should be in the mindset that this is the only data available for these categories.</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>The dataset consists of JPEG images and associated labels. Each image is 600px in its longest dimension. Each image has one category label corresponding to the species. The image ids and labels ids are assigned randomly to ensure they do not match any existing datasets or online resources.</p>\n<p>The dataset contains approximately 530,000 images and 5419 classes. Each image is approximately 100-200kb in size.  Each class contains between 6 and 1000 images in the training set.* </p>\n\n<p>Note: There is no specific validation set provided. It is up to participants to split the training set as they wish.</p>\n\n<p>* Class 0 is the 'not-a-lep' class containing approximately 15,000 images from multiple non Lepidoptera species of insects and plants. </p>\n\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>training_annotations.json.gz</strong> - the training/validation set annotations (including image urls)</li>\n<li><strong>test_annotations.json.gz</strong> - the test set annotations (including image urls, no category annotations)</li>\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>\n<li><strong><a href=\"https://s3.amazonaws.com/fieldguide-fgvc2019/training.tar\">training.tar</a></strong> - 19GB - all training/validation images (external link)</li>\n<li><strong><a href=\"https://s3.amazonaws.com/fieldguide-fgvc2019/testing.tar\">testing.tar</a></strong> - 2.3GB - all testing images (external link)</li>\n</ul>\n\n<h2>Image Format</h2>\nAll images have been saved in the JPEG format and have been resized to have a maximum dimension of 600 pixels.\n\nAnnotation Format\nWe closely follow the annotation format of the COCO dataset. The annotations are stored in the JSON format and are organized as follows:\n\n    {\n      \"info\" : info,\n      \"images\" : [image],\n      \"categories\" : [category],\n      \"annotations\" : [annotation],\n      \"licenses\" : [license]\n    }\n\n    info{\n      \"year\" : int,\n      \"version\" : str,\n      \"description\" : str,\n      \"contributor\" : str,\n      \"url\" : str,\n      \"date_created\" : datetime,\n    }\n\n    image{\n      \"id\" : int,\n      \"width\" : int,\n      \"height\" : int,\n      \"file_name\" : str,\n      \"license\" : int,\n    }\n\n    category{\n      \"id\" : int,\n      \"name\" : str,\n      \"supercategory\" : str,\n    }\n\n    annotation{\n      \"id\" : int,\n      \"image_id\" : int,\n      \"category_id\" : int\n    }\n\n    license{\n      \"id\" : int,\n      \"name\" : str,\n      \"url\" : str\n    }\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>We are conducting the very first Fieldguide Challenge, a FGVCx challenge focusing on fine-grained classification of Lepidoptera (moths &amp; butterflies). There are an estimated 175,000 species of Lepidoptera (leps), most of which are rarely photographed. Species identification is further complicated by distinct adult and immature stages (caterpillars), and often a lack of concrete visual diagnostics for separation between near-identical species. The goal of the competition is to push state-of-the-art classification of real world data that contains high class imbalance and high infraclass variability.</p>\n<p>Moths and butterflies are by far the most photographed group of animals outside of birds.  Having an effective CV component to identification apps would engage tens of thousands of avid citizen scientists. It would allow us to create effective monitoring programs through promotion of night-lighting for moths, which are sensitive environmental indicators. We estimate that at least 50,000 species of moths and butterflies can be identified by images, and we have citizen science groups throughout the world ready to put their smartphone cameras to use.</p>\n<p>The Fieldguide Challenge dataset contains over 5000 species, with a combined training and testing set of over 530,000 images that have been collected and verified by multiple authors of Fieldguide. The dataset features visually-similar species, many of which are highly polymorphic, various stages in the species’ lifecycle (larvae vs adult), as well as species that are often misidentified as a moth/butterfly (e.g. caddisflies).</p>\n<p>The winning team may have the opportunity to present their results at the FGVC workshop at CVPR in Long Beach. The host would like to work with winning teams to build better models for Fieldguide.ai.</p>\n\n<h2>Competition Objectives</h2>\n<ul>\n<li>Improve classification accuracy over a dataset that contains high class imbalance and high heterogeneity (caterpillar vs. adult, wild vs pinned specimens, etc.)</li>\n<li>Improve error detection accuracy - what is not-a-lep*</li>\n</ul>\n<p>*Not-a-lep is a single, mixed-bag class containing images commonly mistaken as leps. For example: leafhoppers, caddisflies, data labels, and flowers often included in the background of moth/butterfly photos, etc.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>We follow a similar metric to the classification tasks of the ILSVRC. For each image, an algorithm will produce 3 labels. For this competition each image has one ground truth label. For a given image, if the ground truth label is found among the 3 predicted labels, then the error for that image is 0, otherwise it is 1. The final score is the error averaged across all images.</p>\n\n<h1>Submission Format</h1>\n<p>For each image in the test set, you must predict 3 class labels. The csv file should contain a header and have the following format:</p>\n<pre>id,predicted<br>12345, 6 27 88<br>67890, 0 100 17<br></pre>\n<p>The id column corresponds to the test image id. The predicted column corresponds to 3 category ids, separated by spaces. You should have one row for each test image. Please sort your predictions from most confident to least, from left to right, this will allow us to study top-1, top-2, and top-3 accuracy.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}