Learning Efficient Unsupervised Satellite Image-based Building Damage Detection

• URL: http://arxiv.org/abs/2312.01576v1
• Date: Mon, 4 Dec 2023 02:20:35 GMT
• Title: Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
• Authors: Yiyun Zhang, Zijian Wang, Yadan Luo, Xin Yu, Zi Huang
• Abstract summary: Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions. In this paper, we investigate a challenging yet practical scenario of U-BDD, where only unlabelled pre- and post-disaster satellite image pairs are provided. We present a novel self-supervised framework, U-BDD++, which improves upon the U-BDD baseline by addressing domain-specific issues associated with satellite imagery.
• Score: 43.06758527206676
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions, hence largely limiting their applications. In this paper, we investigate a challenging yet practical scenario of BDD, Unsupervised Building Damage Detection (U-BDD), where only unlabelled pre- and post-disaster satellite image pairs are provided. As a pilot study, we have first proposed an advanced U-BDD baseline that leverages pre-trained vision-language foundation models (i.e., Grounding DINO, SAM and CLIP) to address the U-BDD task. However, the apparent domain gap between satellite and generic images causes low confidence in the foundation models used to identify buildings and their damages. In response, we further present a novel self-supervised framework, U-BDD++, which improves upon the U-BDD baseline by addressing domain-specific issues associated with satellite imagery. Furthermore, the new Building Proposal Generation (BPG) module and the CLIP-enabled noisy Building Proposal Selection (CLIP-BPS) module in U-BDD++ ensure high-quality self-training. Extensive experiments on the widely used building damage assessment benchmark demonstrate the effectiveness of the proposed method for unsupervised building damage detection. The presented annotation-free and foundation model-based paradigm ensures an efficient learning phase. This study opens a new direction for real-world BDD and sets a strong baseline for future research.

Related papers

• Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector [97.92369017531038]
  We build a new laRge-scale Adervsarial images dataset with Diverse hArmful Responses (RADAR) We then develop a novel iN-time Embedding-based AdveRSarial Image DEtection (NEARSIDE) method, which exploits a single vector that distilled from the hidden states of Visual Language Models (VLMs) to achieve the detection of adversarial images against benign ones in the input.
  arXiv  Detail & Related papers  (2024-10-30T10:33:10Z)
• SOOD: Towards Semi-Supervised Oriented Object Detection [57.05141794402972]
  This paper proposes a novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework. Our experiments show that when trained with the two proposed losses, SOOD surpasses the state-of-the-art SSOD methods under various settings on the DOTA-v1.5 benchmark.
  arXiv  Detail & Related papers  (2023-04-10T11:10:42Z)
• Detecting Building Changes with Off-Nadir Aerial Images [37.58581646229069]
  tilted viewing of off-nadir aerial images brings severe challenges to the building change detection problem. We present a multi-task guided change detection network model, named as MTGCD-Net. Our model achieves superior performance over the previous state-of-the-art competitors.
  arXiv  Detail & Related papers  (2023-01-26T04:04:14Z)
• xFBD: Focused Building Damage Dataset and Analysis [7.862669992685641]
  We propose an auxiliary challenge to the original xView2 competition. This new challenge involves a new dataset and metrics indicating solution performance when damage is more local and limited than in xBD. Methods that succeed on this challenge will provide more fine-grained, precise damage information than original xView2 solutions.
  arXiv  Detail & Related papers  (2022-12-23T21:01:18Z)
• Self-Supervised Learning for Building Damage Assessment from Large-scale xBD Satellite Imagery Benchmark Datasets [3.2248805768155826]
  We propose a self-supervised comparative learning approach to address the task without the requirement of labeled data. We constructed a novel asymmetric twin network architecture and tested its performance on the xBD dataset.
  arXiv  Detail & Related papers  (2022-05-31T11:08:35Z)
• Buildings Classification using Very High Resolution Satellite Imagery [0.769672852567215]
  We focus on buildings damage assessment (BDA) and buildings type classification (BTC) of residential and non-residential buildings. We propose a 2-stage deep learning-based approach, where first, buildings' footprints are extracted using a semantic segmentation model. We validate the proposed approach on two applications showing excellent accuracy and F1-score metrics.
  arXiv  Detail & Related papers  (2021-11-29T16:07:04Z)
• Temporal Action Detection with Multi-level Supervision [116.55596693897388]
  We introduce the Semi-supervised Action Detection (SSAD) task with a mixture of labeled and unlabeled data. We analyze different types of errors in the proposed SSAD baselines which are directly adapted from the semi-supervised classification task. We incorporate weakly-labeled data into SSAD and propose Omni-supervised Action Detection (OSAD) with three levels of supervision.
  arXiv  Detail & Related papers  (2020-11-24T04:45:17Z)
• Assessing out-of-domain generalization for robust building damage detection [78.6363825307044]
  Building damage detection can be automated by applying computer vision techniques to satellite imagery. Models must be robust to a shift in distribution between disaster imagery available for training and the images of the new event. We argue that future work should focus on the OOD regime instead.
  arXiv  Detail & Related papers  (2020-11-20T10:30:43Z)
• 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.