{
  "id": 325625,
  "title": "Performance evaluation: Human vs. Machine",
  "url": "/competitions/snakeclef2022/discussion/325625",
  "author_name": "",
  "post_date": "2022-05-17T11:06:42.170663700Z",
  "votes": 2,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Dear Participants,</p>\n<p>Let me invite you to participate in the Human - LifeCLEF 2022 Snake ID Challenge! We need humans (novices and experts) to identify the same images to compare humans with AI-based algorithms. This project will help you practice your snake ID skills and will also provide valuable data on which species are most commonly misidentified as which other species.</p>\n<p>If you decide to join, you will be shown a picture of a snake and its country of origin. Your task is to recognize the snake species. Use of google search or citizen science platform to identify it is expected. Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems, e.g., Google Image Search, iNaturalist recognition tool, HerpMapper recognition toll etc.</p>\n<p><strong>Through June 15th</strong>, you will identify 150 images of snakes from around the world. </p>\n<p><strong>We'll publish bios of the top 3 IDers, and the top IDers get a book of their choice.</strong></p>\n<p><strong>More detail and link to the snake ID page at the end of the consent</strong> <a href=\"https://forms.gle/awongX8Fk3tX2zGG6\" target=\"_blank\">form/survey</a></p>\n<p>Please be sure to use the same email address for the consent form and the lab.citizenscience.ch website where the snake IDs are so that we can match your IDs with your responses to the survey.</p>\n<p>Thank you for considering your participation!</p>",
  "messages": [
    {
      "id": "1792851",
      "postDate": "05/17/2022 11:06:42",
      "content": "<p>Dear Participants,</p>\n<p>Let me invite you to participate in the Human - LifeCLEF 2022 Snake ID Challenge! We need humans (novices and experts) to identify the same images to compare humans with AI-based algorithms. This project will help you practice your snake ID skills and will also provide valuable data on which species are most commonly misidentified as which other species.</p>\n<p>If you decide to join, you will be shown a picture of a snake and its country of origin. Your task is to recognize the snake species. Use of google search or citizen science platform to identify it is expected. Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems, e.g., Google Image Search, iNaturalist recognition tool, HerpMapper recognition toll etc.</p>\n<p><strong>Through June 15th</strong>, you will identify 150 images of snakes from around the world. </p>\n<p><strong>We'll publish bios of the top 3 IDers, and the top IDers get a book of their choice.</strong></p>\n<p><strong>More detail and link to the snake ID page at the end of the consent</strong> <a href=\"https://forms.gle/awongX8Fk3tX2zGG6\" target=\"_blank\">form/survey</a></p>\n<p>Please be sure to use the same email address for the consent form and the lab.citizenscience.ch website where the snake IDs are so that we can match your IDs with your responses to the survey.</p>\n<p>Thank you for considering your participation!</p>",
      "rawMarkdown": "Dear Participants,\n\nLet me invite you to participate in the Human - LifeCLEF 2022 Snake ID Challenge! We need humans (novices and experts) to identify the same images to compare humans with AI-based algorithms. This project will help you practice your snake ID skills and will also provide valuable data on which species are most commonly misidentified as which other species.\n\nIf you decide to join, you will be shown a picture of a snake and its country of origin. Your task is to recognize the snake species. Use of google search or citizen science platform to identify it is expected. Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems, e.g., Google Image Search, iNaturalist recognition tool, HerpMapper recognition toll etc.\n\n**Through June 15th**, you will identify 150 images of snakes from around the world. \n\n**We'll publish bios of the top 3 IDers, and the top IDers get a book of their choice.**\n\n**More detail and link to the snake ID page at the end of the consent** [form/survey](https://forms.gle/awongX8Fk3tX2zGG6)\n\nPlease be sure to use the same email address for the consent form and the lab.citizenscience.ch website where the snake IDs are so that we can match your IDs with your responses to the survey.\n\nThank you for considering your participation!",
      "votes": null
    },
    {
      "id": "1794472",
      "postDate": "05/18/2022 21:31:51",
      "content": "<p>I simply loved that different Project idea:</p>\n<p>Recognize the snake species, by \"google search or citizen science platform to identify\"</p>\n<p>\"Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems\"</p>\n<p>\"(novices and experts) to identify the same images to compare humans with AI-based algorithms\"</p>\n<p>Can't wait to see the results. </p>",
      "rawMarkdown": "I simply loved that different Project idea:\n\nRecognize the snake species, by \"google search or citizen science platform to identify\"\n\n\"Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems\"\n\n\"(novices and experts) to identify the same images to compare humans with AI-based algorithms\"\n\nCan't wait to see the results.",
      "votes": null
    },
    {
      "id": "1794924",
      "postDate": "05/19/2022 09:10:26",
      "content": "<p>Dear <a href=\"https://www.kaggle.com/mpwolke\" target=\"_blank\">@mpwolke</a>, </p>\n<p>thank you for your interest. <br>\nFYI - The next step will be to compare \"novices\" using AI with experts :)</p>\n<p>LP</p>",
      "rawMarkdown": "Dear @mpwolke, \n\nthank you for your interest. \nFYI - The next step will be to compare \"novices\" using AI with experts :)\n\nLP",
      "votes": null
    },
    {
      "id": "1795188",
      "postDate": "05/19/2022 14:05:12",
      "content": "<p>I had already filled my consent on the form survey.<br>\nAnyone can already compare \"my expertise\", after the four Notebooks I shared on this competition.<br>\nBetter say lack of any knowledge, almost clueless.</p>\n<p>It's not an easy dataset. I was a pity that few made public code with it.<br>\nMaybe on this 2nd part we could see more newbies (like me) participating on it.</p>\n<p>.</p>",
      "rawMarkdown": "I had already filled my consent on the form survey.\nAnyone can already compare \"my expertise\", after the four Notebooks I shared on this competition.\nBetter say lack of any knowledge, almost clueless.\n\nIt's not an easy dataset. I was a pity that few made public code with it.\nMaybe on this 2nd part we could see more newbies (like me) participating on it.\n \n.",
      "votes": null
    },
    {
      "id": "1796066",
      "postDate": "05/20/2022 12:39:15",
      "content": "<p>Indeed, the dataset is hard, but it kind of represents the global species distribution. Including some mimic species. </p>\n<p>Anyway, for local residents, the identification should be fine. I would say I'm pretty good at identifying EU species but clueless for the rest of the word. Sadly there is very few species in EU.</p>\n<p>Lukas</p>",
      "rawMarkdown": "Indeed, the dataset is hard, but it kind of represents the global species distribution. Including some mimic species. \n\nAnyway, for local residents, the identification should be fine. I would say I'm pretty good at identifying EU species but clueless for the rest of the word. Sadly there is very few species in EU.\n\nLukas",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1794472,
      "author_name": "mpwolke",
      "author_url": "",
      "post_date": "05/18/2022 21:31:51",
      "content": "<p>I simply loved that different Project idea:</p>\n<p>Recognize the snake species, by \"google search or citizen science platform to identify\"</p>\n<p>\"Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems\"</p>\n<p>\"(novices and experts) to identify the same images to compare humans with AI-based algorithms\"</p>\n<p>Can't wait to see the results. </p>",
      "votes": null,
      "replies": [
        {
          "id": 1794924,
          "author_name": "picekl",
          "author_url": "",
          "post_date": "05/19/2022 09:10:26",
          "content": "<p>Dear <a href=\"https://www.kaggle.com/mpwolke\" target=\"_blank\">@mpwolke</a>, </p>\n<p>thank you for your interest. <br>\nFYI - The next step will be to compare \"novices\" using AI with experts :)</p>\n<p>LP</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1795188,
          "author_name": "mpwolke",
          "author_url": "",
          "post_date": "05/19/2022 14:05:12",
          "content": "<p>I had already filled my consent on the form survey.<br>\nAnyone can already compare \"my expertise\", after the four Notebooks I shared on this competition.<br>\nBetter say lack of any knowledge, almost clueless.</p>\n<p>It's not an easy dataset. I was a pity that few made public code with it.<br>\nMaybe on this 2nd part we could see more newbies (like me) participating on it.</p>\n<p>.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1796066,
          "author_name": "picekl",
          "author_url": "",
          "post_date": "05/20/2022 12:39:15",
          "content": "<p>Indeed, the dataset is hard, but it kind of represents the global species distribution. Including some mimic species. </p>\n<p>Anyway, for local residents, the identification should be fine. I would say I'm pretty good at identifying EU species but clueless for the rest of the word. Sadly there is very few species in EU.</p>\n<p>Lukas</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1792851": "Dear Participants,\n\nLet me invite you to participate in the Human - LifeCLEF 2022 Snake ID Challenge! We need humans (novices and experts) to identify the same images to compare humans with AI-based algorithms. This project will help you practice your snake ID skills and will also provide valuable data on which species are most commonly misidentified as which other species.\n\nIf you decide to join, you will be shown a picture of a snake and its country of origin. Your task is to recognize the snake species. Use of google search or citizen science platform to identify it is expected. Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems, e.g., Google Image Search, iNaturalist recognition tool, HerpMapper recognition toll etc.\n\n**Through June 15th**, you will identify 150 images of snakes from around the world. \n\n**We'll publish bios of the top 3 IDers, and the top IDers get a book of their choice.**\n\n**More detail and link to the snake ID page at the end of the consent** [form/survey](https://forms.gle/awongX8Fk3tX2zGG6)\n\nPlease be sure to use the same email address for the consent form and the lab.citizenscience.ch website where the snake IDs are so that we can match your IDs with your responses to the survey.\n\nThank you for considering your participation!",
    "1794472": "I simply loved that different Project idea:\n\nRecognize the snake species, by \"google search or citizen science platform to identify\"\n\n\"Any existing \"tool: is allowed with one exception -- Machine Learning-Based systems\"\n\n\"(novices and experts) to identify the same images to compare humans with AI-based algorithms\"\n\nCan't wait to see the results.",
    "1794924": "Dear @mpwolke, \n\nthank you for your interest. \nFYI - The next step will be to compare \"novices\" using AI with experts :)\n\nLP",
    "1795188": "I had already filled my consent on the form survey.\nAnyone can already compare \"my expertise\", after the four Notebooks I shared on this competition.\nBetter say lack of any knowledge, almost clueless.\n\nIt's not an easy dataset. I was a pity that few made public code with it.\nMaybe on this 2nd part we could see more newbies (like me) participating on it.\n \n.",
    "1796066": "Indeed, the dataset is hard, but it kind of represents the global species distribution. Including some mimic species. \n\nAnyway, for local residents, the identification should be fine. I would say I'm pretty good at identifying EU species but clueless for the rest of the word. Sadly there is very few species in EU.\n\nLukas"
  },
  "source": "meta"
}