面向场景专用遥感 MLLM 的能力缺口驱动后训练 FBA：先补齐再进阶

View PDF HTML (experimental)

Abstract:Remote sensing multimodal large language models (RS-MLLMs) have advanced aerial-image understanding, but scenario specialization remains constrained by scarce high-quality supervision and incomplete capability coverage. We propose filling before advancing (FBA), a capability-gap-driven post-training route that develops prerequisite capabilities before scenario-specific adaptation. For coastal harbor understanding, we construct CPRS (Coastal-Port Remote Sensing), a three-layer dataset covering RGB, SAR, PAN, and NIR imagery. FBA organizes supervision into RS semantic anchoring, multi-source bridging, and evidence-grounded scenario tuning. We also introduce HarborEval, an eight-track benchmark assessing perception, spatial understanding, robustness, and generation. Using the same final-task supervision pool, FBA raises the HarborEval score from 57.95 to 70.29 on LLaVA-v1.5 and from 81.09 to 83.37 on Qwen3-VL compared with Direct-SFT. It also outperforms collapsed training and leads the evaluated comparisons on harbor-related VRSBench and RSVQA subsets and expert-scored OpenEval. Stage-wise and supervision-replacement analyses examine the contributions of the supervision roles. A lightweight urban instantiation further supports cross-scenario applicability, with the proposed stage order achieving stronger overall performance than the tested alternatives. Project resources and release updates are available at this https URL.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2607.22205 [cs.CV]
	(or arXiv:2607.22205v3 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2607.22205 arXiv-issued DOI via DataCite

Submission history

From: Yuheng Zong [view email]
[v1] Fri, 24 Jul 2026 11:21:25 UTC (8,237 KB)
[v2] Tue, 28 Jul 2026 11:05:01 UTC (8,237 KB)
[v3] Thu, 15 Oct 2026 10:06:16 UTC (8,773 KB)