BDANet: Multiscale Convolutional Neural Network With Cross-Directional Attention for Building Damage Assessment From Satellite Images

Abstract

Fast and effective responses are required when a natural disaster (e.g., earthquake, hurricane, etc.) strikes. Building damage assessment from satellite imagery is critical before relief effort is deployed. With a pair of pre-and postdisaster satellite images, building damage assessment aims at predicting the extent of damage to buildings. With the powerful ability of feature representation, deep neural networks have been successfully applied to building damage assessment. Most existing works simply concatenate pre-and post-disaster images as input of a deep neural network without considering their correlations. In this paper, we propose a novel two-stage convolutional neural network for Building Damage Assessment, called BDANet. In the first stage, a U-Net is used to extract the locations of buildings. Then the network weights from the first stage are shared in the second stage for building damage assessment. In the second stage, a two-branch multi-scale U-Net is employed as backbone, where pre-and post-disaster images are fed into the network separately. A cross-directional attention module is proposed to explore the correlations between pre-and post-disaster images. Moreover, CutMix data augmentation is exploited to tackle the challenge of difficult classes. The proposed method achieves stateof-the-art performance on a large-scale dataset -xBD. The code is available at https://github.com/ShaneShen/BDANet-Building-Damage-Assessment.

COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

“…Using cut regions for training images and mixing pixel-level information from other sample enables the network to identify targets from local views, which can improve localization and generalization capabilities of the model [ [59] , [60] , [61] , [62] , [63] ]. Classical representative local region pixel-level mixing methods include Mixup [ 64 ], Cutout [ 65 ] and CutMix [ 66 ].…”

BSSNet: Building Subclass Segmentation From Satellite Images Using Boundary Guidance and Contrastive Learning

“…xBD Dataset: Moreover, we present quantitative and qualitative comparisons of building disaster damage assessment on the xBD dataset. We compare our method with the xBD baseline [10], BDANet [56], RescueNet [54] and the method of Weber et al [55], which are popular and typical methods in building disaster damage assessment. All results indicate that our method can be competitive in building disaster damage assessment.…”

On Transfer Learning for Building Damage Assessment from Satellite Imagery in Emergency Contexts

“…They performed an ablation study over different architecture hyperparameters and loss functions, but did not compare their performance with the state-of-the-art. Xiao et al [35] and Shen et al [36] also presented innovative model architectures to solve the problem. The former used a dynamic cross-fusion mechanism (DCFNet) and the latter a multiscale convolutional network with cross-directional attention (BDANet).…”

“…Classification F 1 Weber [30] 0.835 0.697 RescueNet [29] 0.840 0.740 BDANet [36] 0.864 0.782 DCFNet [35] 0.864 0.795 DamFormer [63] 0.869 0.728 Our model 0.846 (0.002) 0.709 (0.003)…”