{
  "fetched_at": "2026-10-19T07:45:35Z",
  "source_url": "https://www.kaggle.com/competitions/com3025-2022-challenge-week-6-7-extended-extend/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# Directory Structure\n- train_data\n  - The image files for the training set\n- train.csv\n  - The labels for the training set\n- test_data\n  - The image files for the test set\n- submission_sample.csv\n  - The sample of submission file\n\n---\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Overview\nThis challenge concerns the automated recognition of visual objects in images using machine learning techniques. The dataset you will work including 23 types of objects in realistic scenes, where training samples and their ground truth are provided. You will develop a machine learning model that will make predictions on unseen test data. The performance will be measured upon submission of the prediction results. A leaderboard will be published after each submission. **You need to use your URN as the Team Name** in the Kaggle page. **Otherwise, your score won't be recorded.** Multiple submissions are encouraged if you wish to improve your models. The latest model for each student will be used for the assessment. You may save multiple prediction results and choose the best one for the final submission.\n\nYou can use Swin-Transformer in this week's lab sheet to do this challenge.\n\n# Important Rule\nYou need to use your URN as the Team Name in the Kaggle page. Otherwise, your score won't be recorded.\n\n# Code Submission\nYou need to submit your code to Surreylearn before the code submission due date (see SurreyLearn for further detail)\n\n# Participation\nPlease click the join competition button on the page to join it. Otherwise, you cannot submit your result.\n\n\n# Task \n### Overview\nThis is a dataset about **Visual Object Classification**. The goal of this challenge is to recognize objects from a number of visual object classes in realistic scenes. There are twenty-three object classes in the datasets:\n* person, hand, foot, head\n* bird, cat, cow, dog, horse, sheep\n* aeroplane, bicycle, boat, bus, car, motorbike, train\n* bottle, chair, dining table, potted plant, sofa, tv/monitor\n\n\n### Dataset Size\n- Training set: 5011 images\n- Testing set: 4952 images\n### Training and Testing Data\nWe will provide the images and labels for the training set and images for the testing set.\n\n# Evaluation\nWe will evaluate your prediction result on the testing set. So you will need to submit the result on this competition page. **The minimum requirement of this challenge is 1.0 Mean ColumnWise Log Loss (lower result indicate better performance).**\n \n# Submission Format\nYour submission should be a csv file, with 24 columns in it, the first is the id of the test image and the second to 24th are the predicted probability of each visual object class (e.g., person 0.49, cat 0.97, dog 0.01). We will provide an example of the submission file in the Data Section.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "# The evaluation metric for this competition is Mean ColumnWise Log Loss.\n\n## Submission Format\n\nsubmission files should contain twenty-four columns: `file_name` and `label` for each type of visual object. A header will be needed for the submission, so the first line will start with the header information.\n\nWe provide a template of the submission file in the Data Section. **You must follow the order of tags in the template in your submission**.\n\nThe file header **must** contain a header and have the following format:\n```\nfile_name, person, hand, foot, ...\n000191.jpg, 0.48365255458278655, 0.055888978482053875, 0.5992317190609185 ...\n003498.jpg, 0.6553363657832338, 0.8178946666280492, 0.8834546850516083, ...\n005957.jpg, 0.8320555710717549, 0.8207940776278797, 0.21887284952453545, ...\n...\n```\n\nAn example submission is provided on the data page.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "# Important Rule\nYou need to use your URN as the Team Name in the Kaggle page. Otherwise, your score won't be recorded.\n\n# Code Submission\nYou need to submit your code to Surreylearn before the code submission due date (see SurreyLearn for further detail)\n\n# Participation\nPlease click the join competition button on the page to join it. Otherwise, you cannot submit your result.\n\n# Task \n### Overview\nThis is a dataset about **Visual Object Classification**. The goal of this challenge is to recognize objects from a number of visual object classes in realistic scenes. There are twenty-three object classes in the datasets:\n\n### Dataset Size\n- Training set: 5011 images\n- Testing set: 4952 images\n\n### Training and Testing Data\nWe will provide the images and labels for the training set and images for the testing set.\n\n# Evaluation\nWe will evaluate your prediction result on the testing set. So you will need to submit the result on this competition page. **The minimum requirement of this challenge is 1.0 Mean ColumnWise Log Loss (lower result indicate better performance).**\n \n# Submission Format\nYour submission should be a csv file, with 24 columns in it, the first is the id of the test image and the second to 24th are the predicted probability of each visual object class (e.g., person 0.49, cat 0.97, dog 0.01). We will provide an example of the submission file in the Data Section.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}