论文标题
从多光谱和SAR图像中的不变表示的自我监督学习
Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images
论文作者
论文摘要
自我监督的学习（SSL）已成为几个领域分类和分割任务中的新最先进。其中，SSL中的一个流行类别是蒸馏网络，例如BYOL。这项工作提出了RSDNET，该RSDNET应用于遥感（RS）域中的蒸馏网络（BYOL），其中数据与天然RGB图像无关。由于多光谱（MS）和合成孔径雷达（SAR）传感器提供各种光谱和空间分辨率信息，因此我们将它们用作隐式增强，以学习不变特征嵌入。为了通过SSL学习基于RS的不变功能，我们通过两种方式训练了RSDNET，即单频道功能学习和三个通道功能学习。与使用三个或更多频段的常见概念相比，这项工作探讨了从随机MS和SAR频段学习的单个通道特征学习的有用性。在我们的线性评估中，这些单个通道功能在欧洲裔分类任务上达到了0.92 F1分数，对于某些单个频段，在DFC分段任务上达到了59.6 MIOU。我们还将结果与成像网的重量进行了比较，并表明基于RS的SSL模型的表现优于基于有监督的Imagenet模型。与单个模态数据相比，我们进一步探讨了多模式数据的实用性，并且表明，利用MS和SAR数据比仅利用MS数据更好的不变表示。
Self-Supervised learning (SSL) has become the new state-of-art in several domain classification and segmentation tasks. Of these, one popular category in SSL is distillation networks such as BYOL. This work proposes RSDnet, which applies the distillation network (BYOL) in the remote sensing (RS) domain where data is non-trivially different from natural RGB images. Since Multi-spectral (MS) and synthetic aperture radar (SAR) sensors provide varied spectral and spatial resolution information, we utilised them as an implicit augmentation to learn invariant feature embeddings. In order to learn RS based invariant features with SSL, we trained RSDnet in two ways, i.e., single channel feature learning and three channel feature learning. This work explores the usefulness of single channel feature learning from random MS and SAR bands compared to the common notion of using three or more bands. In our linear evaluation, these single channel features reached a 0.92 F1 score on the EuroSAT classification task and 59.6 mIoU on the DFC segmentation task for certain single bands. We also compared our results with ImageNet weights and showed that the RS based SSL model outperforms the supervised ImageNet based model. We further explored the usefulness of multi-modal data compared to single modality data, and it is shown that utilising MS and SAR data learn better invariant representations than utilising only MS data.
