{
  "fetched_at": "2026-10-19T09:20:48Z",
  "source_url": "https://www.kaggle.com/competitions/cs470-mvtec/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# Context\nAutomatic detection of the defect with no detectives samples often requires detecting them in Industrial anomaly detection\nThis dataset is for educational purposes\n\n# Acknowledgements\nBased on the public dataset by the MVTec company\nPaul Bergmann, Michael Fauser, David Sattlegger, Carsten Steger. MVTec AD - A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection; in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019\n\n# Inspiration\nThe main goal of this dataset is to explore self-supervised learning on capsule images in order to solve anomaly detection problems.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Kaggle AD Challenge: Unsupervised Image Anomaly Detection Competition\n## Project Goals:\n- Students compete at Kaggle, a predictive model and analysis contest platform, and have hands-on experience and acquire deep learning knowledge through solving real-world image anomaly detection problem. Competition will be done by performing anomaly segmentation task for one category of MVTec AD image dataset. Evaluate project by measuring segmentation pixelwise AUROC(area under a receiver operating characteristic curve) performance.\n\n## Dataset and Experimental Environment:\n- Dataset: MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection. It contains over 5000 high-resolution images divided into fifteen different object and texture categories. Each category comprises a set of defect-free training images and a test set of images with various kinds of defects as well as images without defects. In this competition, we compete using only one category (capsule) of the MVtec AD dataset. There is no anomaly in the train dataset.\n- Experimental Environment:  Kaggle InClass competition, IPython notebook. Pytorch. Code for data loader and evaluation function will be provided.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Evaluate project by measuring Segmentation pixelwise AUROC(area under a receiver operating characteristic curve) performance. The Area Under the Curve (AUC) is the measure of the ability of a classifier to distinguish between classes and is used as a summary of the ROC curve. The higher the AUC, the better the performance of the model at distinguishing between the positive and negative classes.\n\nRead more here:\n\n[AUC-ROC Curve in Machine Learning Clearly Explained](https://www.analyticsvidhya.com/blog/2020/06/auc-roc-curve-machine-learning/)\n\n[ML Crash course](https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc)\n\n[Understanding AUCROC](https://towardsdatascience.com/understanding-auc-roc-curve-68b2303cc9c5)\n\n[Lets learn about AUCROC article](https://medium.com/greyatom/lets-learn-about-auc-roc-curve-4a94b4d88152)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "# Don't cheat!\n\n- No sharing outside teams. sharing code or data outside of teams is not permitted. \n- Use of external data is permitted. This includes use of pre-trained models.\n- Hand-labeling is not permitted and will be grounds for disqualification.\n- Final submissions must be mailed to the TA in a reproducible form.\n- Using test data set as validation set is not permitted. \n- (Kaggle scores are for simple comparison purposes only) Final score should be included in the report and presentation materials. \n\n# Have fun :)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prizes",
      "content": "- Pass - If your score is better than TA's\n- Fail - Otherwise",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}