mlsanityData to 7 Oct 2026

Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents

arXiv 2201.04236 ↗First posted 11 Jan 2022cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Natural disasters, such as floods, tornadoes, or wildfires, are increasingly pervasive as the Earth undergoes global warming. It is difficult to predict when and where an incident will occur, so timely emergency response is critical to saving the lives of those endangered by destructive events. Fortunately, technology can play a role in these situations. Social media posts can be used as a low-latency data source to understand the progression and aftermath of a disaster, yet parsing this data is tedious without automated methods. Prior work has mostly focused on text-based filtering, yet image and video-based filtering remains largely unexplored. In this work, we present the Incidents1M Dataset, a large-scale multi-label dataset which contains 977,088 images, with 43 incident and 49 place categories. We provide details of the dataset construction, statistics and potential biases; introduce and train a model for incident detection; and perform image-filtering experiments on millions of images on Flickr and Twitter. We also present some applications on incident analysis to encourage and enable future work in computer vision for humanitarian aid. Code, data, and models are available at http://incidentsdataset.csail.mit.edu.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 43 of its 101 references that are in the map. First posted on arXiv 11 Jan 2022.

Builds on

43 of 101 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  8. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  9. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  10. 2017Learning multiple visual domains with residual adapterscited by 553
  11. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  12. 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181
31 more
  1. 2019Does Object Recognition Work for Everyone?cited by 149
  2. 2019xBD: A Dataset for Assessing Building Damage from Satellite Imagerycited by 138
  3. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
  4. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  5. 2019Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screeningcited by 94
  6. 2017Fine-Grained Car Detection for Visual Census Estimationcited by 76
  7. 2017Using Deep Learning and Google Street View to Estimate the Demographic Makeup of the UScited by 66
  8. 2014Processing Social Media Messages in Mass Emergency: A Surveycited by 50
  9. 2019Building Damage Detection in Satellite Imagery Using Convolutional Neural Networkscited by 34
  10. 2020Multimodal Categorization of Crisis Events in Social Mediacited by 34
  11. 2019Natural Disasters Detection in Social Media and Satellite imagery: a surveycited by 27
  12. 2020Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusioncited by 27
  13. 2020Detecting natural disasters, damage, and incidents in the wildcited by 23
  14. 2018Multi3Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagerycited by 22
  15. 2020Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Responsecited by 19
  16. 2018A Pragmatic Guide to Geoparsing Evaluationcited by 17
  17. 2017A Unified Model for Near and Remote Sensingcited by 14
  18. 2019Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networkscited by 12
  19. 2020Comprehensive Semantic Segmentation on High Resolution UAV Imagery for Natural Disaster Damage Assessmentcited by 12
  20. 2018From Satellite Imagery to Disaster Insightscited by 9
  21. 2020Water level prediction from social media images with a multi-task ranking approachcited by 8
  22. 2017Exploiting ConvNet Diversity for Flooding Identificationcited by 7
  23. 2019Deep Landscape Features for Improving Vector-borne Disease Predictioncited by 5
  24. 2019Inundation Modeling in Data Scarce Regionscited by 4
  25. 2019Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detectorcited by 3
  26. 2018Mapping Informal Settlements in Developing Countries with Multi-resolution, Multi-spectral Datacited by 2
  27. 2019FireNet: Real-time Segmentation of Fire Perimeter from Aerial Videocited by 2
  28. 2018Exploring object-centric and scene-centric CNN features and their complementarity for human rights violations recognition in imagescited by 1
  29. 2019DisplaceNet: Recognising Displaced People from Images by Exploiting Dominance Levelcited by 1
  30. 2019AI-based evaluation of the SDGs: The case of crop detection with earth observation datacited by 1
  31. 2019Explainable Semantic Mapping for First Responderscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 6; 2025: 8; 2026: 7.

25 papers.

Sort:

By area:

  1. 2024A social context-aware graph-based multimodal attentive learning framework for disaster content classification during emergencies: a benchmark dataset and methodcited by 12
  2. 2024CRASAR-U-DROIDs: A Large Scale Benchmark Dataset for Building Alignment and Damage Assessment in Georectified sUAS Imagerycited by 9
  3. 2024QuakeSet: A Dataset and Low-Resource Models to Monitor Earthquakes through Sentinel-1cited by 8
  4. 2025Towards Evaluating Proactive Risk Awareness of Multimodal Language Modelscited by 6
  5. 2024CrisisViT: A Robust Vision Transformer for Crisis Image Classificationcited by 5
  6. 2022NADBenchmarks -- a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasterscited by 4
  7. 2024Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Datacited by 4
  8. 2022Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Datacited by 3
  9. 2025RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situationcited by 3
  10. 2024LADI v2: Multi-label Dataset and Classifiers for Low-Altitude Disaster Imagerycited by 2
  11. 2025An Explainable Deep Neural Network with Frequency-Aware Channel and Spatial Refinement for Flood Prediction in Sustainable Citiescited by 2
  12. 2023CrashCar101: Procedural Generation for Damage Assessmentcited by 1
13 more
  1. 2026DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenescited by 1
  2. 2023Leveraging CNNs and Ensemble Learning for Automated Disaster Image Classificationcited by 0
  3. 2025AI and Remote Sensing for Resilient and Sustainable Built Environments: A Review of Current Methods, Open Data and Future Directionscited by 0
  4. 2025MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrievalcited by 0
  5. 2025Multimodal Learning with Augmentation Techniques for Natural Disaster Assessmentcited by 0
  6. 2025Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasterscited by 0
  7. 2025MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understandingcited by 0
  8. 2026MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignmentcited by 0
  9. 2026Open-Vocabulary vs Supervised Learning Methods for Post-Disaster Visual Scene Understandingcited by 0
  10. 2026Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applicationscited by 0
  11. 2026Forged Calamity: Benchmark for Cross-Domain Synthetic Disaster Detection in the Age of Diffusioncited by 0
  12. 2026Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillationcited by 0
  13. 2026Assessing the Benefits of Combining Advanced Deep Learning Techniques for Post-Disaster Building Damage Assessment from UAV Imagerycited by 0