{
  "fetched_at": "2026-10-19T07:22:15Z",
  "source_url": "https://www.kaggle.com/competitions/11785-hw2p2-face-recognition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Train and dev folders have 7001 identities with 20 and 5 images, respectively. You are given 35000 image files in the test folder to classify.\nPlease adhere to the format of the sample submission",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this homework, you will work on **pattern recognition problems** that require position invariance. Specifically, you will work on the problem of recognizing faces in images. In typical pictures of faces, the face is rarely perfectly centered. Different pictures of the same person may have the face shifted by varying amounts. The classifier must recognize the face regardless of this indeterminacy of position.  This calls for position-invariant models, specifically Convolutional Neural Networks, or CNNs.\n\nFace classification is a **closed-set multiclass classification problem**, where the subjects in the test set have also been seen in the training set, although the precise pictures in the test set will not be in the training set. For this to achieve high accuracy it is only required that the embeddings for (all pictures of) the subjects in our \"vocabulary\" be linearly separable from each other.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Evaluation metric: Classification Accuracy",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This is the Face Recognition Kaggle Competition for 11-785 Spring 2024",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}