An important step for limiting the negative impact of natural disasters is rapid damage assessment after a disaster occurred. For instance, building damage detection can be automated by applying computer vision techniques to satellite imagery. Such models operate in a multi-domain setting: every disaster is inherently different (new geolocation, unique circumstances), and models must be robust to a shift in distribution between disaster imagery available for training and the images of the new event. Accordingly, estimating real-world performance requires an out-of-domain (OOD) test set. However, building damage detection models have so far been evaluated mostly in the simpler yet unrealistic in-distribution (IID) test setting. Here we argue that future work should focus on the OOD regime instead. We assess OOD performance of two competitive damage detection models and find that existing state-of-the-art models show a substantial generalization gap: their performance drops when evaluated OOD on new disasters not used during training. Moreover, IID performance is not predictive of OOD performance, rendering current benchmarks uninformative about real-world performance. Code and model weights are available at https://github.com/ecker-lab/robust-bdd.
Carnegie Mellon University（卡内基梅隆大学）；Software Engineering Institute（软件工程研究所）；Defense Innovation Unit（国防创新部门）；Department of Defense（国防部）；CrowdAI, Inc.（CrowdAI公司）
We present xBD, a new, large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research. Natural disaster response requires an accurate understanding of damaged buildings in an affected region. Current response strategies require in-person damage assessments within 24-48 hours of a disaster. Massive potential exists for using aerial imagery combined with computer vision algorithms to assess damage and reduce the potential danger to human life. In collaboration with multiple disaster response agencies, xBD prov…
Element AI（元素人工智能公司）；Quebec Artificial Intelligence Institute (Mila)（魁北克人工智能研究所（米拉））；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；Stanford University（斯坦福大学）
The CLEVR dataset of natural-looking questions about 3D-rendered scenes has recently received much attention from the research community. A number of models have been proposed for this task, many of which achieved very high accuracies of around 97-99%. In this work, we study how systematic the generalization of such models is, that is to which extent they are capable of handling novel combinations of known linguistic constructs. To this end, we test models' understanding of referring expressions based on matching object properties (such as e.g. "another cube that is the same size as the brown …
The Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）；Queens University（女王大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
We propose a novel method for enforcing AI fairness with respect to protected or sensitive factors. This method uses a dual strategy performing training and representation alteration (TARA) for the mitigation of prominent causes of AI bias by including: a) the use of representation learning alteration via adversarial independence to suppress the bias-inducing dependence of the data representation from protected factors; and b) training set alteration via intelligent augmentation to address bias-causing data imbalance, by using generative models that allow the fine control of sensitive factors …
Google Research（谷歌研究院）；Stanford University（斯坦福大学）；United Nations World Food Programme（联合国世界粮食计划署）
To respond to disasters such as earthquakes, wildfires, and armed conflicts, humanitarian organizations require accurate and timely data in the form of damage assessments, which indicate what buildings and population centers have been most affected. Recent research combines machine learning with remote sensing to automatically extract such information from satellite imagery, reducing manual labor and turn-around time. A major impediment to using machine learning methods in real disaster response scenarios is the difficulty of obtaining a sufficient amount of labeled data to train a model for a…
Picture based vehicle protection handling is a significant region with enormous degree for mechanization. In this paper we consider the issue of vehicle harm characterization, where a portion of the classifications can be fine-granular. We investigate profound learning based procedures for this reason. At first, we attempt legitimately preparing a CNN. In any case, because of little arrangement of marked information, it doesn't function admirably. At that point, we investigate the impact of space explicit pre-preparing followed by tweaking. At last, we explore different avenues regarding move …
Kansas State University（堪萨斯州立大学）；Qatar Computing Research Institute（卡塔尔计算研究所）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
Traditional post-disaster assessment of damage heavily relies on expensive GIS data, especially remote sensing image data. In recent years, social media has become a rich source of disaster information that may be useful in assessing damage at a lower cost. Such information includes text (e.g., tweets) or images posted by eyewitnesses of a disaster. Most of the existing research explores the use of text in identifying situational awareness information useful for disaster response teams. The use of social media images to assess disaster damage is limited. In this paper, we propose a novel appro…
In this paper, we study the problem of efficiently assessing building damage after natural disasters like hurricanes, floods or fires, through aerial video analysis. We make two main contributions. The first contribution is a new dataset, consisting of user-generated aerial videos from social media with annotations of instance-level building damage masks. This provides the first benchmark for quantitative evaluation of models to assess building damage using aerial videos. The second contribution is a new model, namely MSNet, which contains novel region proposal network designs and an unsupervi…
In the aftermath of disasters, building damage maps are obtained using change detection to plan rescue operations. Current convolutional neural network approaches do not consider the similarities between neighboring buildings for predicting the damage. We present a novel graph-based building damage detection solution to capture these relationships. Our proposed model architecture learns from both local and neighborhood features to predict building damage. Specifically, we adopt the sample and aggregate graph convolution strategy to learn aggregation functions that generalize to unseen graphs w…
Simon Fraser University（西蒙弗雷泽大学）；Texas A&M University（德克萨斯A&M大学）
This paper presents \dahitra, a novel deep-learning model with hierarchical transformers to classify building damages based on satellite images in the aftermath of natural disasters. Satellite imagery provides real-time and high-coverage information and offers opportunities to inform large-scale post-disaster building damage assessment, which is critical for rapid emergency response. In this work, a novel transformer-based network is proposed for assessing building damage. This network leverages hierarchical spatial features of multiple resolutions and captures the temporal differences in the …
The Academy for Mathematics, Science, and Engineering（数学、科学与工程学院）
Natural disasters ravage the world's cities, valleys, and shores on a regular basis. Deploying precise and efficient computational mechanisms for assessing infrastructure damage is essential to channel resources and minimize the loss of life. Using a dataset that includes labeled pre- and post- disaster satellite imagery, we take a machine learning-based remote sensing approach and train multiple convolutional neural networks (CNNs) to assess building damage on a per-building basis. We present a novel methodology of interpretable deep learning that seeks to explicitly investigate the most usef…
Robert Bosch GmbH, Automated Driving Research（罗伯特·博世有限公司，自动驾驶研究）；University of Lübeck, Institute of Signal Processing（吕贝克大学，信号处理研究所）
Deep Neural Networks (DNNs) achieve state-of-the-art performance on numerous applications. However, it is difficult to tell beforehand if a DNN receiving an input will deliver the correct output since their decision criteria are usually nontransparent. A DNN delivers the correct output if the input is within the area enclosed by its generalization envelope. In this case, the information contained in the input sample is processed reasonably by the network. It is of large practical importance to assess at inference time if a DNN generalizes correctly. Currently, the approaches to achieve this go…
Assessing Generalization Capabilities of Malaria Diagnostic Models from Thin Blood Smears
MyC；APHP Paris, La Pitié-Salpêtrière, Sorbonne Université（APHP巴黎，拉皮蒂埃-萨尔佩特里耶，索邦大学）；CHU of Montpellier, University of Montpellier（蒙彼利埃大学附属医院，蒙彼利埃大学）；CHU Campus, Ministère de la Santé et de l'hygiène Publique（CHU校区，卫生与公共卫生部）；CHU Sylvanus Olympio, Lomé, Togo（索维拉尼奥利奥医院，洛美，多哥）；Faculté des Sciences de la Santé, Université de Lomé（健康科学学院，洛美大学）
Assessing the generalization performance of SAM for ureteroscopy scene understanding
Tecnologico de Monterrey, School of Engineering and Sciences（墨西哥技术学院，工程与科学学院）；CRAN UMR 7039, Université de Lorraine and CNRS（洛林大学CRAN UMR 7039及CNRS）；CHRU de Nancy-Brabois, service d’urologie（南布拉欧斯医院泌尿科）
Pedestrian crossing prediction has been a topic of active research, resulting in many new algorithmic solutions. While measuring the overall progress of those solutions over time tends to be more and more established due to the new publicly available benchmark and standardized evaluation procedures, knowing how well existing predictors react to unseen data remains an unanswered question. This evaluation is imperative as serviceable crossing behavior predictors should be set to work in various scenarii without compromising pedestrian safety due to misprediction. To this end, we conduct a study …
Accurate and fine-grained information about the extent of damage to buildings is essential for directing Humanitarian Aid and Disaster Response (HADR) operations in the immediate aftermath of any natural calamity. In recent years, satellite and UAV (drone) imagery has been used for this purpose, sometimes aided by computer vision algorithms. Existing Computer Vision approaches for building damage assessment typically rely on a two stage approach, consisting of building detection using an object detection model, followed by damage assessment through classification of the detected building tiles…
Improved MambdaBDA Framework for Robust Building Damage Assessment Across Disaster Domains
Department of Computer Engineering, Istanbul Technical University（计算机工程系，伊斯坦布尔技术大学）；Division of Engineering, New York University Abu Dhabi（工程学院，纽约大学阿布扎比分校）
Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）；BJIT Limited（BJIT有限公司）
During a disaster event, images shared on social media helps crisis managers gain situational awareness and assess incurred damages, among other response tasks. Recent advances in computer vision and deep neural networks have enabled the development of models for real-time image classification for a number of tasks, including detecting crisis incidents, filtering irrelevant images, classifying images into specific humanitarian categories, and assessing the severity of damage. Despite several efforts, past works mainly suffer from limited resources (i.e., labeled images) available to train more…
Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones
School of Computer Science and Technology（计算机科学与技术学院）；Zhejiang University（浙江大学）；School of Software Technology（软件学院）；School of Information Engineering（信息工程学院）；North China University of Water Resources and Electric Power（北方水利电力大学）；Polytechnic Institute；Institute of Systems Engineering（系统工程院）；Academy of Military Sciences（军事科学院）；Department of Geo-spatial Information（测绘信息学院）；Information Engineering University（信息工程大学）；School of Instrumentation Science and Engineering（仪器科学与工程学院）；Harbin Institute of Technology（哈尔滨工业大学）；Harbin Institute of Technology Suzhou Research Institute（哈尔滨工业大学苏州研究院）
AB2CD: AI for Building Climate Damage Classification and Detection
IBM Consulting, Germany（IBM咨询公司（德国））；Karlsruhe Institute of Technology, Germany（卡尔斯鲁厄理工学院）；IBM Research – Europe, Switzerland（IBM欧洲研究院）；University of Bayreuth, Germany（拜罗伊特大学）
Revealing Model Biases: Assessing Deep Neural Networks via Recovered Sample Analysis
University of Tehran（德黑兰大学）；University of Bremen（不来梅大学）；Okinawa Institute of Science and Technology (OIST)（冲绳科学技术大学院大学）；Institute For Research In Fundamental Sciences (IPM)（基础科学研究所）
Bridge Damage Detection from Low-Light UAV Imagery via Degradation-Aware Mixture-of-Experts Enhancement
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Sustainability X-Lab, The University of Hong Kong（香港大学可持续发展X实验室）；School of Architecture, Building, and Civil Engineering, Loughborough University（拉夫堡大学建筑、建造与土木工程学院）；Department of Engineering Science, University of Oxford（牛津大学工程科学系）；Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology（香港科技大学土木与环境工程系）
Manipal Institute of Technology（马尼帕尔理工学院）；Manipal Academy of Higher Education（马尼帕尔高等教育学院）；Manipal Institute of Technology Bengaluru（马尼帕尔理工学院（班加罗尔））
Identification of regions affected by floods is a crucial piece of information required for better planning and management of post-disaster relief and rescue efforts. Traditionally, remote sensing images are analysed to identify the extent of damage caused by flooding. The data acquired from sensors onboard earth observation satellites are analyzed to detect the flooded regions, which can be affected by low spatial and temporal resolution. However, in recent years, the images acquired from Unmanned Aerial Vehicles (UAVs) have also been utilized to assess post-disaster damage. Indeed, a UAV bas…
Architectural Insights for Post-Tornado Damage Recognition
The University of Alabama（亚拉巴马大学）；Colorado State University（科罗拉多州立大学）；Argonne National Laboratory（阿贡国家实验室）；Old Dominion University（老 Dominion 大学）；University of South Alabama（南方亚拉巴马大学）
Qatar Computing Research Institute, HBKU（哈马德·本·卡利法大学卡塔尔计算研究所）；BJIT Limited（BJIT有限公司）
Images shared on social media help crisis managers gain situational awareness and assess incurred damages, among other response tasks. As the volume and velocity of such content are typically high, real-time image classification has become an urgent need for a faster disaster response. Recent advances in computer vision and deep neural networks have enabled the development of models for real-time image classification for a number of tasks, including detecting crisis incidents, filtering irrelevant images, classifying images into specific humanitarian categories, and assessing the severity of t…
Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Cornell University（康奈尔大学）；Yale University（耶鲁大学）；University of California Irvine（加州大学伊万哥罗市分校）；Brown University（布朗大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge
RIKEN Center for Advanced Intelligence Project (AIP), RIKEN（理化学研究所先进智能项目中心（AIP），理化学研究所）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science and Technology（南京信息工程大学遥感与测绘工程学院）
