Identifying Disaster Damage Images Using a Domain Adaptation Approach
Identifying Disaster Damage Images Using a Domain Adaptation Approach
复制标题
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Xukun Li;Cornelia Caragea
中科院分区：
文献类型：
--
作者：
Xukun Li;Cornelia Caragea
迫切需要有效过滤灾害目击者实时发布的有用态势感知信息的方法。虽然许多研究都集中在文本信息的过滤上，但对灾难图像的过滤研究却比较有限。特别是，在没有可用于目标灾难的标记数据的情况下，对领域自适应在紧急目标灾难中过滤图像的适用性进行了研究。为了填补这一空白，我们提出应用一种称为领域对抗神经网络（DANN）的领域自适应方法来识别显示损伤的图像。DANN方法以VGG-19为骨干，并使用对抗性训练来找到使源数据和目标数据无法区分的转换。在几对灾难上的实验结果表明，与在源标记数据上进行微调的VGG-19模型相比，DANN模型通常给出类似或更好的结果。
Approaches for effectively filtering useful situational awareness information posted by eyewitnesses of disasters, in real time, are greatly needed. While many studies have focused on filtering textual information, the research on filtering disaster images is more limited. In particular, there are no studies on the applicability of domain adaptation to filter images from an emergent target disaster, when no labeled data is available for the target disaster. To fill in this gap, we propose to apply a domain adaptation approach, called domain adversarial neural networks (DANN), to the task of identifying images that show damage. The DANN approach has VGG-19 as its backbone, and uses the adversarial training to find a transformation that makes the source and target data indistinguishable. Experimental results on several pairs of disasters suggest that the DANN model generally gives similar or better results as compared to the VGG-19 model fine-tuned on the source labeled data.