论文标题
改进用于遥感语义细分的流动纱模块
Improved-Flow Warp Module for Remote Sensing Semantic Segmentation
论文作者
论文摘要
遥感语义分割的目的是在带有特定标签的航空图像上自动分配每个像素。在这封信中，我们提出了一个新模块，称为“改进流经”模块（IFWM），以调整跨不同尺度上的语义特征图，以进行遥感语义分割。在卷积神经网络中，应用了改进的流动纱模块以及特征提取过程。首先，IFWM通过可学习的方式计算像素的偏移，这可以减轻多尺度功能的未对准。其次，偏移有助于低分辨率的深度功能上采样过程，以提高功能符合性，从而提高了语义分割的准确性。我们在几个遥感数据集上验证了我们的方法，结果证明了我们方法的有效性。
Remote sensing semantic segmentation aims to assign automatically each pixel on aerial images with specific label. In this letter, we proposed a new module, called improved-flow warp module (IFWM), to adjust semantic feature maps across different scales for remote sensing semantic segmentation. The improved-flow warp module is applied along with the feature extraction process in the convolutional neural network. First, IFWM computes the offsets of pixels by a learnable way, which can alleviate the misalignment of the multi-scale features. Second, the offsets help with the low-resolution deep feature up-sampling process to improve the feature accordance, which boosts the accuracy of semantic segmentation. We validate our method on several remote sensing datasets, and the results prove the effectiveness of our method..
