Abstract
Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of pretraining data. This work introduces Subimage Overlap Prediction, a novel self-supervised pretraining task to aid semantic segmentation in remote sensing imagery that uses significantly lesser pretraining imagery. Given an image, a sub-image is extracted and the model is trained to produce a semantic mask of the location of the extracted sub-image within the original image. We demonstrate that pretraining with this task results in significantly faster convergence, and equal or better performance (measured via mIoU) on downstream segmentation. This gap in convergence and performance widens when labeled training data is reduced. We show this across multiple architecture types, and with multiple downstream datasets. We also show that our method matches or exceeds performance while requiring significantly lesser pretraining data relative to other SSL methods. Code and model weights are provided at \href{this https URL}{this http URL}.
Abstract (translated)
自监督学习（SSL）方法已成为创建通用模型的主导范式，这些模型的能力可以转移到下游的监督学习任务中。然而，大多数这样的方法依赖于大量的预训练数据。本工作引入了一种新颖的自监督预训练任务——子图像重叠预测（Subimage Overlap Prediction），旨在帮助遥感图像中的语义分割，并且使用显著较少的预训练图像。给定一张图片后，从中抽取一个子图像，模型被训练以生成表示该子图在原图中位置的语义掩码。 我们证明了利用此任务进行预训练可以实现更快的收敛速度，并且在下游分割任务上的表现（通过mIoU衡量）至少与现有方法持平或更好。当减少标注训练数据时，这种差距会进一步扩大。我们在多种架构类型和多个下游数据集上展示了这一点。此外，我们的方法在需要显著较少预训练数据的情况下仍能达到匹配甚至超过其他SSL方法的性能。 代码和模型权重可在[此处](this https URL)获取。
URL
https://arxiv.org/abs/2601.01781
