论文标题
持续的Barlow双胞胎：遥感语义细分的持续自学学习
Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation
论文作者
论文摘要
在地球观测领域（EO）中，已经提出了连续学习（CL）算法来处理大型数据集，通过将它们分解为几个子集并逐步处理它们。这些算法中的大多数假定数据是（a）来自单个来源，并且（b）完全标记。相反，现实世界中的EO数据集的特征是较大的异质性（例如，来自空中，卫星或无人机场景），在大多数情况下它们是未标记的，这意味着它们只能通过新兴的自我经验化的学习（SSL）范式完全利用它们。由于这些原因，在本文中，我们提出了一种新算法，用于合并SSL和CL用于遥感应用程序，我们称之为连续的Barlow Twins（CBT）。它结合了最简单的自我实施技术之一，即Barlow Twins的优势，以及弹性重量巩固方法，以避免灾难性的遗忘。此外，我们首次在高度异构的EO数据集上评估SSL方法，显示了这些策略在三个几乎不重叠的域数据集的新型组合中的有效性（机源性Potsdam数据集，卫星US3D数据集和无线无线无线无线无线无线电话），对crucial distream seciation see eo eo，令人鼓舞的结果表明，在这种情况下，SSL的优势以及基于RESNET50创建增量有效预审慎提取器的有效性，而无需依靠所有数据的完整可用性，并保存时间和资源。
In the field of Earth Observation (EO), Continual Learning (CL) algorithms have been proposed to deal with large datasets by decomposing them into several subsets and processing them incrementally. The majority of these algorithms assume that data is (a) coming from a single source, and (b) fully labeled. Real-world EO datasets are instead characterized by a large heterogeneity (e.g., coming from aerial, satellite, or drone scenarios), and for the most part they are unlabeled, meaning they can be fully exploited only through the emerging Self-Supervised Learning (SSL) paradigm. For these reasons, in this paper we propose a new algorithm for merging SSL and CL for remote sensing applications, that we call Continual Barlow Twins (CBT). It combines the advantages of one of the simplest self-supervision techniques, i.e., Barlow Twins, with the Elastic Weight Consolidation method to avoid catastrophic forgetting. In addition, for the first time we evaluate SSL methods on a highly heterogeneous EO dataset, showing the effectiveness of these strategies on a novel combination of three almost non-overlapping domains datasets (airborne Potsdam dataset, satellite US3D dataset, and drone UAVid dataset), on a crucial downstream task in EO, i.e., semantic segmentation. Encouraging results show the superiority of SSL in this setting, and the effectiveness of creating an incremental effective pretrained feature extractor, based on ResNet50, without the need of relying on the complete availability of all the data, with a valuable saving of time and resources.
