Joint-Optimized Unsupervised Adversarial Domain Adaptation in Remote Sensing Segmentation with Prompted Foundation Model

TL;DR

This paper introduces a joint-optimized adversarial network leveraging the Segment Anything Model for unsupervised domain adaptation in remote sensing segmentation, effectively addressing feature inconsistencies and domain gaps across diverse datasets.

Contribution

It proposes a novel SAM-based adversarial framework with a finetuning decoder and prompted segmentor for improved unsupervised domain adaptation in remote sensing.

Findings

Enhanced segmentation accuracy on benchmark datasets

Robustness demonstrated across multiple remote sensing domains

Improved interpretability of the segmentation process

Abstract

Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation (UDA-RSSeg) addresses the challenge of adapting a model trained on source domain data to target domain samples, thereby minimizing the need for annotated data across diverse remote sensing scenes. This task presents two principal challenges: (1) severe inconsistencies in feature representation across different remote sensing domains, and (2) a domain gap that emerges due to the representation bias of source domain patterns when translating features to predictive logits. To tackle these issues, we propose a joint-optimized adversarial network incorporating the "Segment Anything Model (SAM) (SAM-JOANet)" for UDA-RSSeg. Our approach integrates SAM to leverage its robust generalized representation capabilities, thereby alleviating feature inconsistencies. We introduce a finetuning decoder designed to convert SAM-Encoder features into predictive logits. Additionally, a feature-level adversarial-based prompted segmentor is employed to generate class-agnostic maps, which guide the finetuning decoder's feature representations. The network is optimized end-to-end, combining the prompted segmentor and the finetuning decoder. Extensive evaluations on benchmark datasets, including ISPRS (Potsdam/Vaihingen) and CITY-OSM (Paris/Chicago), demonstrate the effectiveness of our method. The results, supported by visualization and analysis, confirm the method's interpretability and robustness. The code of this paper is available at https://github.com/CV-ShuchangLyu/SAM-JOANet.