We introduce a novel neural network architecture -- Spectral ENcoder for SEnsor Independence (SEnSeI) -- by which several multispectral instruments, each with different combinations of spectral bands, can be used to train a generalised deep learning model. We focus on the problem of cloud masking, using several pre-existing datasets, and a new, freely available dataset for Sentinel-2. Our model is shown to achieve state-of-the-art performance on the satellites it was trained on (Sentinel-2 and Landsat 8), and is able to extrapolate to sensors it has not seen during training such as Landsat 7, Per\'uSat-1, and Sentinel-3 SLSTR. Model performance is shown to improve when multiple satellites are used in training, approaching or surpassing the performance of specialised, single-sensor models. This work is motivated by the fact that the remote sensing community has access to data taken with a hugely variety of sensors. This has inevitably led to labelling efforts being undertaken separately for different sensors, which limits the performance of deep learning models, given their need for huge training sets to perform optimally. Sensor independence can enable deep learning models to utilise multiple datasets for training simultaneously, boosting performance and making them much more widely applicable. This may lead to deep learning approaches being used more frequently for on-board applications and in ground segment data processing, which generally require models to be ready at launch or soon afterwards.
翻译:我们引入了新型神经网络结构 -- -- Sensor 独立卫星的光谱ENcoder(SenSeniSeI) -- -- 通过这种结构,可以使用若干多光谱仪器,每个仪器都有不同的光谱波段组合,来训练一个一般的深层次学习模式。我们侧重于云面遮罩问题,使用一些已有的数据集,并为哨兵-2提供一个新的免费数据集。我们的模型显示能够在其所培训的卫星(Sentinel-2和Landsat 8)上取得最先进的性能,并且能够对在培训期间没有看到过的传感器进行外推,例如Landsat 7、Per\uSat-1和Sentinel-3 SLSTre等。示范性能显示,当多颗卫星在培训中使用、接近或超过专门、单一传感器模型的性能时,将提高云面面面面面面面掩体的功能。我们的工作动力在于,遥感界能够利用极具多样化的传感器获取的数据。这不可避免地导致为不同的传感器单独进行标记工作,这限制了深层学习模型的性能模型的性能,这限制了深度模型的性能,因为在深度培训中经常需要进行深度的深度的推进数据操作。