Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data

• URL: http://arxiv.org/abs/2202.00050v1
• Date: Mon, 31 Jan 2022 19:21:44 GMT
• Title: Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data
• Authors: Soroor Shekarizadeh, Razieh Rastgoo, Saif Al-Kuwari, Mohammad Sabokrou
• Abstract summary: We propose an unsupervised deep neural network to detect and localize damages in social media images. Our approach outperforms state-of-the-art methods in detecting and localizing the damaged areas.
• Score: 14.308913482163558
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Impact of a DCT-driven Loss in Attention-based Knowledge-Distillation for Scene Recognition [64.29650787243443]
  We propose and analyse the use of a 2D frequency transform of the activation maps before transferring them. This strategy enhances knowledge transferability in tasks such as scene recognition. We publicly release the training and evaluation framework used along this paper at http://www.vpu.eps.uam.es/publications/DCTBasedKDForSceneRecognition.
  arXiv  Detail & Related papers  (2022-05-04T11:05:18Z)
• Engineering deep learning methods on automatic detection of damage in infrastructure due to extreme events [0.38233569758620045]
  This paper presents a few experimental studies for automated Structural Damage Detection (SDD) in extreme events using deep learning methods. In the first study, a 152-layer Residual network (ResNet) is utilized to classify multiple classes in eight SDD tasks. The results show that the accuracy of damage detection is significantly improved compared to only using a segmentation network.
  arXiv  Detail & Related papers  (2022-05-01T19:55:56Z)
• Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery [0.0]
  We use a dataset that includes labeled pre- and post-disaster satellite imagery to assess building damage on a per-building basis. We train multiple convolutional neural networks (CNNs) to assess building damage on a per-building basis. Our research seeks to computationally contribute to aiding in this ongoing and growing humanitarian crisis, heightened by anthropogenic climate change.
  arXiv  Detail & Related papers  (2022-01-24T16:55:56Z)
• NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks [0.0]
  The paper demonstrates a systematic effort to achieve efficient building damage classification. Results demonstrate data and computational efficiency with 10% of the collected data combined with a GAN reducing the time of computation from roughly half a day to about 1 hour.
  arXiv  Detail & Related papers  (2021-10-27T15:29:16Z)
• Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation [76.2621758731288]
  We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA) We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
  arXiv  Detail & Related papers  (2021-08-03T17:09:56Z)
• Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles [69.9674326582747]
  This paper presents a visual framework to investigate neural network models subjected to adversarial examples. We show how observing these elements can quickly pinpoint exploited areas in a model.
  arXiv  Detail & Related papers  (2021-03-18T13:04:21Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• 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)
• Information Obfuscation of Graph Neural Networks [96.8421624921384]
  We study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data. We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance.
  arXiv  Detail & Related papers  (2020-09-28T17:55:04Z)
• Improving Emergency Response during Hurricane Season using Computer Vision [0.06882042556551608]
  We have developed a framework for crisis response and management that incorporates the latest technologies in computer vision (CV), inland flood prediction, damage assessment and data visualization. Our computer-vision model analyzes spaceborne and airborne imagery to detect relevant features during and after a natural disaster. We have designed an ensemble of models to identify features including water, roads, buildings, and vegetation from the imagery.
  arXiv  Detail & Related papers  (2020-08-17T15:42:02Z)
• RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery [83.49145695899388]
  RescueNet is a unified model that can simultaneously segment buildings and assess the damage levels to individual buildings and can be trained end-to-end. RescueNet is tested on the large scale and diverse xBD dataset and achieves significantly better building segmentation and damage classification performance than previous methods.
  arXiv  Detail & Related papers  (2020-04-15T19:52:09Z)

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.