ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Images
This work addresses the challenge of scalable segmentation for remote sensing applications, offering an incremental improvement by adapting a foundation model with minimal supervision.
The paper tackled the problem of adapting the Segment Anything Model (SAM) to remote sensing imagery, which suffers from domain shifts and lack of dense annotations, by proposing a point-supervised self-prompting framework that uses only sparse point annotations; the method consistently outperformed pretrained SAM and recent point-supervised methods on three benchmark datasets.
Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the scarcity of dense annotations. To address this limitation, we propose a point-supervised self-prompting framework that adapts SAM to RSI using only sparse point annotations. Our method employs a Refine-Requery-Reinforce loop, in which coarse pseudo-masks are generated from initial points (Refine), improved with self-constructed box prompts (Requery), and embeddings are aligned for Soft Semantic Alignment to mitigate error propagation. (Reinforce). Without relying on full-mask supervision, our approach progressively enhances SAM's segmentation quality and domain robustness through self-guided prompt adaptation. We evaluate our proposed method on three RSI benchmark datasets, WHU, HRSID, and NWPU VHR-10, showing that our method consistently surpasses pretrained SAM and recent point-supervised segmentation methods. Our results demonstrate that self-prompting and semantic alignment provide an efficient path towards scalable, point-level adaptation of foundation segmentation models for remote sensing applications.