# MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos

arXiv: https://arxiv.org/abs/2006.16479 · HTML: https://mlsanity.com/paper/2006.16479/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 25 of 25)

- [RescueNet: A High Resolution UAV Semantic Segmentation Benchmark Dataset for Natural Disaster Damage Assessment](https://mlsanity.com/paper/2202.12361/) (2022)
- [EarthNets: Empowering AI in Earth Observation](https://mlsanity.com/paper/2210.04936/) (2022)
- [DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition](https://mlsanity.com/paper/2203.10233/) (2022)
- [BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images](https://mlsanity.com/paper/2105.07364/) (2021)
- [RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents](https://mlsanity.com/paper/2410.13384/) (2024)
- [CRASAR-U-DROIDs: A Large Scale Benchmark Dataset for Building Alignment and Damage Assessment in Georectified sUAS Imagery](https://mlsanity.com/paper/2407.17673/) (2024)
- [Attention Based Semantic Segmentation on UAV Dataset for Natural Disaster Damage Assessment](https://mlsanity.com/paper/2105.14540/) (2021)
- [NADBenchmarks -- a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasters](https://mlsanity.com/paper/2212.10735/) (2022)
- [Non-Uniform Spatial Alignment Errors in sUAS Imagery From Wide-Area Disasters](https://mlsanity.com/paper/2405.06593/) (2024)
- [DRespNeT: A UAV Dataset and YOLOv8-DRN Model for Aerial Instance Segmentation of Building Access Points for Post-Earthquake Search-and-Rescue Missions](https://mlsanity.com/paper/2508.16016/) (2025)
- [Now you see it, Now you don't: Damage Label Agreement in Drone & Satellite Post-Disaster Imagery](https://mlsanity.com/paper/2505.08117/) (2025)
- [A Multimodal RAG Framework for Housing Damage Assessment: Collaborative Optimization of Image Encoding and Policy Vector Retrieval](https://mlsanity.com/paper/2509.09721/) (2025)
- [Leveraging AI for Natural Disaster Management : Takeaways From The Moroccan Earthquake](https://mlsanity.com/paper/2311.08999/) (2023)
- [Multi-step feature fusion for natural disaster damage assessment on satellite images](https://mlsanity.com/paper/2410.21901/) (2024)
- [ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation](https://mlsanity.com/paper/2507.02294/) (2025)
- [From Pixels to Damage Severity: Estimating Earthquake Impacts Using Semantic Segmentation of Social Media Images](https://mlsanity.com/paper/2507.02781/) (2025)
- [Deploying Rapid Damage Assessments from sUAS Imagery for Disaster Response](https://mlsanity.com/paper/2511.03132/) (2025)
- [Feature Aggregation Network for Building Extraction from High-resolution Remote Sensing Images](https://mlsanity.com/paper/2309.06017/) (2023)
- [Adversarially Masked Video Consistency for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.16242/) (2024)
- [LBurst: Learning-Based Robotic Burst Feature Extraction for 3D Reconstruction in Low Light](https://mlsanity.com/paper/2410.23522/) (2024)
- [Leveraging Self-Supervised Features for Efficient Flooded Region Identification in UAV Aerial Images](https://mlsanity.com/paper/2507.04915/) (2025)
- [EIDSeg: A Pixel-Level Semantic Segmentation Dataset for Post-Earthquake Damage Assessment from Social Media Images](https://mlsanity.com/paper/2511.06456/) (2025)
- [TornadoNet: Real-Time Building Damage Detection with Ordinal Supervision](https://mlsanity.com/paper/2603.11557/) (2026)
- [Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applications](https://mlsanity.com/paper/2605.08196/) (2026)
- [Looks Can be Deceiving: Annotator and Reviewer Performance Across Imagery Sources in Crowd-Sourced Aerial Damage Assessment](https://mlsanity.com/paper/2608.14942/) (2026)

## Abstract (arXiv)

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 unsupervised score refinement network for confidence score calibration in both bounding box and mask branches. We show that our model achieves state-of-the-art results compared to previous methods in our dataset. We will release our data, models and code.