SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model

TL;DR

This paper introduces SAMRS, a large-scale remote sensing segmentation dataset created by leveraging the Segment Anything Model and existing detection data, significantly advancing data availability for remote sensing segmentation tasks.

Contribution

The paper presents a novel pipeline for generating a large-scale remote sensing segmentation dataset, SAMRS, surpassing existing datasets in size and providing comprehensive annotations for various segmentation and detection tasks.

Findings

SAMRS contains over 105,000 images and 1.66 million instances.

Pre-training with SAMRS improves segmentation performance and addresses task discrepancies.

The dataset enables effective training for semantic, instance segmentation, and object detection.

Abstract

The success of the Segment Anything Model (SAM) demonstrates the significance of data-centric machine learning. However, due to the difficulties and high costs associated with annotating Remote Sensing (RS) images, a large amount of valuable RS data remains unlabeled, particularly at the pixel level. In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS. SAMRS totally possesses 105,090 images and 1,668,241 instances, surpassing existing high-resolution RS segmentation datasets in size by several orders of magnitude. It provides object category, location, and instance information that can be used for semantic segmentation, instance segmentation, and object detection, either individually or in combination. We also provide a comprehensive analysis of SAMRS from various aspects. Moreover, preliminary experiments highlight the importance of conducting segmentation pre-training with SAMRS to address task discrepancies and alleviate the limitations posed by limited training data during fine-tuning. The code and dataset will be available at https://github.com/ViTAE-Transformer/SAMRS.