当前位置: X-MOL 学术Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Hybridizing Cross-Level Contextual and Attentive Representations for Remote Sensing Imagery Semantic Segmentation
Remote Sensing ( IF 4.2 ) Pub Date : 2021-07-29 , DOI: 10.3390/rs13152986
Xin Li , Feng Xu , Runliang Xia , Xin Lyu , Hongmin Gao , Yao Tong

Semantic segmentation of remote sensing imagery is a fundamental task in intelligent interpretation. Since deep convolutional neural networks (DCNNs) performed considerable insight in learning implicit representations from data, numerous works in recent years have transferred the DCNN-based model to remote sensing data analysis. However, the wide-range observation areas, complex and diverse objects and illumination and imaging angle influence the pixels easily confused, leading to undesirable results. Therefore, a remote sensing imagery semantic segmentation neural network, named HCANet, is proposed to generate representative and discriminative representations for dense predictions. HCANet hybridizes cross-level contextual and attentive representations to emphasize the distinguishability of learned features. First of all, a cross-level contextual representation module (CCRM) is devised to exploit and harness the superpixel contextual information. Moreover, a hybrid representation enhancement module (HREM) is designed to fuse cross-level contextual and self-attentive representations flexibly. Furthermore, the decoder incorporates DUpsampling operation to boost the efficiency losslessly. The extensive experiments are implemented on the Vaihingen and Potsdam benchmarks. In addition, the results indicate that HCANet achieves excellent performance on overall accuracy and mean intersection over union. In addition, the ablation study further verifies the superiority of CCRM.

中文翻译:

混合跨级上下文和注意力表示用于遥感图像语义分割

遥感影像的语义分割是智能解译的一项基本任务。由于深度卷积神经网络 (DCNN) 在从数据中学习隐式表示方面表现出相当多的洞察力,因此近年来的大量工作已将基于 DCNN 的模型转移到遥感数据分析中。然而,由于观察范围广,物体复杂多样,照明和成像角度影响像素容易混淆,导致效果不佳。因此,提出了一种名为 HCANet 的遥感图像语义分割神经网络,用于为密集预测生成具有代表性和判别性的表示。HCANet 混合了跨级上下文和注意力表示,以强调学习特征的可区分性。首先,设计了一个跨级上下文表示模块(CCRM)来利用和利用超像素上下文信息。此外,混合表示增强模块(HREM)旨在灵活地融合跨级别上下文和自注意力表示。此外,解码器结合了 DUpsampling 操作以无损地提高效率。广泛的实验是在 Vaihingen 和 Potsdam 基准上实施的。此外,结果表明 HCANet 在整体精度和平均交集上取得了优异的表现。此外,消融研究进一步验证了CCRM的优越性。混合表示增强模块(HREM)旨在灵活地融合跨级别上下文和自注意力表示。此外,解码器结合了 DUpsampling 操作以无损地提高效率。广泛的实验是在 Vaihingen 和 Potsdam 基准上实施的。此外,结果表明 HCANet 在整体精度和平均交集上取得了优异的表现。此外,消融研究进一步验证了CCRM的优越性。混合表示增强模块(HREM)旨在灵活地融合跨级别上下文和自注意力表示。此外,解码器结合了 DUpsampling 操作以无损地提高效率。广泛的实验是在 Vaihingen 和 Potsdam 基准上实施的。此外,结果表明 HCANet 在整体精度和平均交集上取得了优异的表现。此外,消融研究进一步验证了CCRM的优越性。结果表明,HCANet 在整体精度和平均交集上取得了优异的性能。此外,消融研究进一步验证了CCRM的优越性。结果表明,HCANet 在整体精度和平均交集上取得了优异的性能。此外,消融研究进一步验证了CCRM的优越性。
更新日期:2021-07-29
down
wechat
bug