用子图重叠预测做自监督预训练，少数据也能高效提升遥感图像语义分割性能。
Subimage Overlap Prediction: Task-Aligned Self-Supervised Pretraining For Semantic Segmentation In Remote Sensing Imagery
- 通过预测子图在原图中的位置来实现自监督预训练。
- 在少量标注数据下，收敛更快且分割准确率更高（mIoU提升）。
- 适合资源有限的遥感图像分割任务，尤其适合小样本场景。
自监督学习（SSL）已成为构建可迁移通用模型的主流范式。然而，多数方法依赖海量预训练数据。本文提出子图重叠预测（Subimage Overlap Prediction）这一新型自监督预训练任务，用于提升遥感图像语义分割性能，显著减少所需预训练影像数量。给定一张图像，从中提取子图像，模型需预测该子图像在原图中的位置并生成语义掩码。实验表明，采用此任务预训练后，下游分割任务收敛速度明显加快，且在相同或更少标注数据条件下，性能（以mIoU衡量）达到或优于现有方法。该优势在标签数据稀缺时更为突出。我们在多种网络架构和多个下游数据集上验证了有效性。相比其他SSL方法，本方法在相近甚至更优性能下，所需预训练数据量大幅减少。代码与模型权重已开源。
原文摘要 · Abstract (English)
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{https://github.com/sharmalakshay93/subimage-overlap-prediction}{github.com/sharmalakshay93/subimage-overlap-prediction}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。