Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data
Not on the map. Why?
Abstract (arXiv)
Social media plays a significant role in sharing essential information, which helps humanitarian organizations in rescue operations during and after disaster incidents. However, developing an efficient method that can provide rapid analysis of social media images in the early hours of disasters is still largely an open problem, mainly due to the lack of suitable datasets and the sheer complexity of this task. In addition, supervised methods can not generalize well to novel disaster incidents. In this paper, inspired by the success of Knowledge Distillation (KD) methods, we propose an unsupervised deep neural network to detect and localize damages in social media images. Our proposed KD architecture is a feature-based distillation approach that comprises a pre-trained teacher and a smaller student network, with both networks having similar GAN architecture containing a generator and a discriminator. The student network is trained to emulate the behavior of the teacher on training input samples, which, in turn, contain images that do not include any damaged regions. Therefore, the student network only learns the distribution of no damage data and would have different behavior from the teacher network-facing damages. To detect damage, we utilize the difference between features generated by two networks using a defined score function that demonstrates the probability of damages occurring. Our experimental results on the benchmark dataset confirm that our approach outperforms state-of-the-art methods in detecting and localizing the damaged areas, especially for novel disaster types.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 41 references that are in the map. First posted on arXiv 31 Jan 2022.
Builds on
25 of 41 references.
References · 25
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2020Knowledge Distillation: A Surveycited by 1,578
- 2017SmoothGrad: removing noise by adding noisecited by 1,097
- 2014Striving for Simplicity: The All Convolutional Netcited by 983
- 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
- 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
- 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 312
13 more
- 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
- 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
- 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
- 2018CrisisMMD: Multimodal Twitter Datasets from Natural Disasterscited by 88
- 2018Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphonecited by 44
- 2021Sign Language Production: A Reviewcited by 26
- 2022Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidentscited by 25
- 2020Detecting natural disasters, damage, and incidents in the wildcited by 23
- 2021MEDIC: A Multi-Task Learning Dataset for Disaster Image Classificationcited by 20
- 2020Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Responsecited by 19
- 2021Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocolcited by 9
- 2017Automatic Image Filtering on Social Networks Using Deep Learning and Perceptual Hashing During Crisescited by 8
- 2018Localizing and Quantifying Damage in Social Media Imagescited by 7
Built on by
Citing papers per year: 2023: 2; 2024: 0; 2025: 1.
3 papers.