MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining

TL;DR

This paper introduces a Multi-Task Pretraining approach for remote sensing foundation models, improving transferability across diverse RS tasks by training on multiple objectives simultaneously.

Contribution

It proposes a novel multi-task pretraining paradigm with shared encoder and task-specific decoders, applicable to CNNs and vision transformers, enhancing downstream RS task performance.

Findings

Outperforms existing models of similar size on 14 datasets.

Achieves competitive results with larger state-of-the-art models.

Validates effectiveness of multi-task pretraining in RS domain.

Abstract

Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervised and self-supervised learning methods to initialize model weights effectively. However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. In this study, we explore the Multi-Task Pretraining (MTP) paradigm for RS foundation models to address this issue. Using a shared encoder and task-specific decoder architecture, we conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. MTP supports both convolutional neural networks and vision transformer foundation models with over 300 million parameters. The pretrained models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection. Extensive experiments across 14 datasets demonstrate the superiority of our models over existing ones of similar size and their competitive performance compared to larger state-of-the-art models, thus validating the effectiveness of MTP.