{
  "fetched_at": "2026-10-20T11:00:17Z",
  "source_url": "https://www.kaggle.com/competitions/fun-ml-hw-4-problem-5-sp-26/data",
  "pages": [
    {
      "name": "data-description",
      "content": "As described in homework notebook, you are doing segmentations on img_1.png and img_2.png; that can be found in HW folder. \n\nStill, img_1.png and img_2.png are attached there for your convenience. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "After having your ideal result, please save your result in `result_img1` and `result_img2` in the cell below.\n\nWe have defined the label for each class in each image. Make sure you use the same settings as us and feel free to use the provided swapping label code to swap labels if needed.\n\n - for `img1.png`, use k=3, background labels as 0, rectangle labels as 1 and triangle labels as 2\n - for `img2.png`, use k=2, background labels as 0, building labels as 1\n\nAfter your `result_img1` and `result_img2` are ready, run the cell below to create a `submission.csv`. Please download it from this notebook and submit it in our [Kaggle](https://www.kaggle.com/t/107607dc5f7da97fdfa41d5870ec8bb2) competition.\n\nPlease remember to note your Kaggle competition nickname in this notebook. We will use your ranking to grade.\n\nYou have 10 submission quota each day to submit your result and get your multi-class classification accuracy and ranking.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "We calculate the multi-class classification accuracy with ground-turth hand-crafted labels in both images by\n\n$$\\text{Accuracy} = \\frac{\\text{# of correctly labeled pixels}}{\\text{total # of pixels}}$$",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- After having your ideal result, please save your result in `result_img1` and `result_img2` in the cell below.\n\n- We have defined the label for each class in each image. Make sure you use the same settings as us and feel free to use the provided swapping label code to swap labels if needed.\n\n - for `img1.png`, use k=3, background labels as 0, rectangle labels as 1 and triangle labels as 2\n - for `img2.png`, use k=2, background labels as 0, building labels as 1\n\n- After your `result_img1` and `result_img2` are ready, run the cell below to create a `submission.csv`. Please download it from this notebook and submit it in our [Kaggle](https://www.kaggle.com/t/107607dc5f7da97fdfa41d5870ec8bb2) competition.\n\n- Please remember to note your Kaggle competition nickname in this notebook. We will use your ranking to grade.\n\n- You have 10 submission quota each day to submit your result and get your multi-class classification accuracy and ranking.\n\n- We calculate the multi-class classification accuracy with ground-turth hand-crafted labels in both images by\n\n$$\\text{Accuracy} = \\frac{\\text{# of correctly labeled pixels}}{\\text{total # of pixels}}$$",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "You are right! This is the place to submit your HW 4 Problem5. \n\nIn previous part of HW 4 Problem 5, you learnt to process images in a form they could be used to train clustering algorithms (with each individual pixel being a 'training example'). For an RGB image, each training example would have at least 3 features (the Red, Green, and Blue values for the pixel). In addition, one could add the spatial positions of the pixel as another set of features. \n\nWe are now going test what you have learnt in processing image by this Kaggle competition wherein you are asked to segment two RGB images. By submitting your result to Kaggle, you will see your multi-class classification accuracy and ranking on the leaderborad. 10 pts will depend on your ranking (top 10% get 10pts, top 11%-20% get 9pts, etc.), and another 5 pts depend on your method explanation and clear, well-labeled plots and images. \n\nSince this is an open-ended question, you should try to design your own features to achieve better classification results. Try different feature combinations, image processing techniques to get the best looking results. Refer to the homework notebook for details. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Citation",
      "content": "T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, and C. L. Zitnick. Microsoft COCO: Common objects in context. In ECCV, 2014.\nOnur Selim KILIÇ. FunML Hw4 Problem 5 Sp23. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Others",
      "content": "This competition has concluded. \n\nThis competition is constructed for the teaching of ECE 4252/6252 for Georgia Institute of Technology, Spring 2026. \n\nFor future usage or other questions of this competition, please contact wuyang_du@gatech.edu",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}