Incidents1M: a large-scale dataset of images with natural disasters,
damage, and incidents
- URL: http://arxiv.org/abs/2201.04236v1
- Date: Tue, 11 Jan 2022 23:03:57 GMT
- Title: Incidents1M: a large-scale dataset of images with natural disasters,
damage, and incidents
- Authors: Ethan Weber, Dim P. Papadopoulos, Agata Lapedriza, Ferda Ofli,
Muhammad Imran, Antonio Torralba
- Abstract summary: 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.
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.
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.
- Score: 28.16346818821349
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- LADI v2: Multi-label Dataset and Classifiers for Low-Altitude Disaster Imagery [0.23108201502462672]
We present the LADI v2 dataset, a curated set of about 10,000 disaster images captured in the United States by the Civil Air Patrol.
We provide two pretrained baseline classifiers and compare their performance to state-of-the-art vision-language models in multi-label classification.
The data and code are released publicly to support the development of computer vision models for emergency management research and applications.
arXiv Detail & Related papers (2024-06-04T20:51:04Z) - CrisisMatch: Semi-Supervised Few-Shot Learning for Fine-Grained Disaster
Tweet Classification [51.58605842457186]
We present a fine-grained disaster tweet classification model under the semi-supervised, few-shot learning setting.
Our model, CrisisMatch, effectively classifies tweets into fine-grained classes of interest using few labeled data and large amounts of unlabeled data.
arXiv Detail & Related papers (2023-10-23T07:01:09Z) - Sarcasm Detection in a Disaster Context [103.93691731605163]
We introduce HurricaneSARC, a dataset of 15,000 tweets annotated for intended sarcasm.
Our best model is able to obtain as much as 0.70 F1 on our dataset.
arXiv Detail & Related papers (2023-08-16T05:58:12Z) - Harnessing the Power of Text-image Contrastive Models for Automatic
Detection of Online Misinformation [50.46219766161111]
We develop a self-learning model to explore the constrastive learning in the domain of misinformation identification.
Our model shows the superior performance of non-matched image-text pair detection when the training data is insufficient.
arXiv Detail & Related papers (2023-04-19T02:53:59Z) - Detecting Damage Building Using Real-time Crowdsourced Images and
Transfer Learning [53.26496452886417]
This paper presents an automated way to extract the damaged building images after earthquakes from social media platforms such as Twitter.
Using transfer learning and 6500 manually labelled images, we trained a deep learning model to recognize images with damaged buildings in the scene.
The trained model achieved good performance when tested on newly acquired images of earthquakes at different locations and ran in near real-time on Twitter feed after the 2020 M7.0 earthquake in Turkey.
arXiv Detail & Related papers (2021-10-12T06:31:54Z) - MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification [6.167082944123002]
We propose MEDIC, the largest social media image classification dataset for humanitarian response.
MEDIC consists of 71,198 images to address four different tasks in a multi-task learning setup.
This is the first dataset of its kind: social media image, disaster response, and multi-task learning research.
arXiv Detail & Related papers (2021-08-29T11:55:50Z) - A Machine learning approach for rapid disaster response based on
multi-modal data. The case of housing & shelter needs [0.0]
One of the most immediate needs of people affected by a disaster is finding shelter.
This paper proposes a machine learning workflow that aims to fuse and rapidly analyse multimodal data.
Based on a database of 19 characteristics for more than 200 disasters worldwide, a fusion approach at the decision level was used.
arXiv Detail & Related papers (2021-07-29T18:22:34Z) - Deep Learning Benchmarks and Datasets for Social Media Image
Classification for Disaster Response [5.610924570214424]
We propose new datasets for disaster type detection, informativeness classification, and damage severity assessment.
We benchmark several state-of-the-art deep learning models and achieve promising results.
We release our datasets and models publicly, aiming to provide proper baselines as well as to spur further research in the crisis informatics community.
arXiv Detail & Related papers (2020-11-17T20:15:49Z) - Event-Related Bias Removal for Real-time Disaster Events [67.2965372987723]
Social media has become an important tool to share information about crisis events such as natural disasters and mass attacks.
Detecting actionable posts that contain useful information requires rapid analysis of huge volume of data in real-time.
We train an adversarial neural model to remove latent event-specific biases and improve the performance on tweet importance classification.
arXiv Detail & Related papers (2020-11-02T02:03:07Z) - Physics-informed GANs for Coastal Flood Visualization [65.54626149826066]
We create a deep learning pipeline that generates visual satellite images of current and future coastal flooding.
By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism.
While this work focused on the visualization of coastal floods, we envision the creation of a global visualization of how climate change will shape our earth.
arXiv Detail & Related papers (2020-10-16T02:15:34Z) - Detecting natural disasters, damage, and incidents in the wild [26.73896031797989]
We present the Incidents dataset, which contains 446,684 images annotated by humans that cover 43 incidents across a variety of scenes.
We employ a baseline classification model that mitigates false-positive errors and we perform image filtering experiments on millions of social media images from Flickr and Twitter.
arXiv Detail & Related papers (2020-08-20T20:09:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.