Attention-based object detection with saliency loss in remote sensing images
Attention-based object detection with saliency loss in remote sensing images
复制标题
DOI：
10.1117/1.jei.30.1.013007
复制
发表时间：
2021-01
影响因子：
1.1
通讯作者：
Qin Wu;X. Yuan;Zikang Yao;Zhilei Chai
中科院分区：
文献类型：
--
作者：
Qin Wu;X. Yuan;Zikang Yao;Zhilei Chai
摘要。由于遥感图像中的目标具有密集性、多方向性和多尺度性，因此遥感图像中的地理空间目标检测是一个具有挑战性的课题。提出了一种用于遥感图像中目标检测的注意力网络。通过通道注意和空间注意，该框架更加关注重要的通道，强调物体的位置信息。同时，提出了显著性学习来增强对象的信息。在损失函数中加入显著性损失，指导网络在训练阶段的学习。此外，在网络中加入多尺度特征模块，捕捉尺度变化。在公共遥感影像数据集上的实验结果验证了该方法的有效性。
Abstract. Geospatial object detection in remote sensing images is a challenging subject since objects in remote sensing images are dense, multioriented, and multiscale. We present an attention network for object detection in remote sensing images. Through channel attention and spatial attention, the framework pays more attention to important channels and emphasizes position information of objects. Meanwhile, saliency learning is proposed to enhance objects information. Furthermore, saliency loss is added to the loss function to guide network learning in the training stage. In addition, multiscale feature module is added into the network to capture scale variations. Experimental results on public remote sensing image datasets validate the effectiveness of the proposed method.