Detecting Natural Disasters, Damage, and Incidents in the Wild

Image | General | Preparedness

Incidents Dataset is dataset for general disaster detection, and disaster classification. It contains 1,144,148 images (with 446,684 images as positives) and is introduced for multiclass classification.

  • ML task type: Multiclass classification
  • Data Source: Google Images
  • Size: 1,144,148 Images
  • Timespan: N/A
  • Geographical Coverage: Global
  • Baseline Information
  • Evaluated on: CNN
  • Metrics used: Accuracy (Incident Classification); Average Precision (Incident Detection)
  • Results as reported in original paper: Accuracy: 77.3 (Incident Classification), mAP: 67.65 (Incident Detection)

Ethan Weber, Nuria Marzo, Dim P Papadopoulos, Aritro Biswas, Agata Lapedriza, Ferda Ofli, Muhammad Imran, and Antonio Torralba. Detecting natural disasters, damage, and incidents in the wild. In European Conference on Computer Vision, pages 331–350. Springer, 2020.