{"paper":{"title":"Axial-Relation Guided Fusion State Space Model for Optical-Elevation Sensing Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ARG-Mamba fuses optical and elevation features along axial relations within a state space model to improve remote sensing segmentation accuracy.","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Feng Gao, Junyu Dong, Qian Du, Yanhai Gan, Zhilin Jin","submitted_at":"2026-05-16T02:42:54Z","abstract_excerpt":"Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency on the ISPRS Vaihingen and Potsdam datasets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that explicitly modeling global cross-modal correlations along horizontal and vertical axes via the Axial-Relation Guided Fusion Module yields superior feature fusion compared with existing cross-modal methods, as described in the module design.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ARG-Mamba combines a multi-scale state space module and an axial-relation guided fusion module to outperform prior methods on optical-elevation semantic segmentation for remote sensing.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ARG-Mamba fuses optical and elevation features along axial relations within a state space model to improve remote sensing segmentation accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4f2b4dcf10b55af4e615e775d1a0d40e5acc917bff30d98073da446d366f6ea5"},"source":{"id":"2605.16768","kind":"arxiv","version":1},"verdict":{"id":"dcef637d-bfba-4844-a14c-cc590b2d5889","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:11:11.145762Z","strongest_claim":"ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency on the ISPRS Vaihingen and Potsdam datasets.","one_line_summary":"ARG-Mamba combines a multi-scale state space module and an axial-relation guided fusion module to outperform prior methods on optical-elevation semantic segmentation for remote sensing.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that explicitly modeling global cross-modal correlations along horizontal and vertical axes via the Axial-Relation Guided Fusion Module yields superior feature fusion compared with existing cross-modal methods, as described in the module design.","pith_extraction_headline":"ARG-Mamba fuses optical and elevation features along axial relations within a state space model to improve remote sensing segmentation accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16768/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.356537Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:21:23.895819Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.312857Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.446546Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"eeec59668cffed740ee6eab14099e2554ff769a4a1eac4c781ca5bf3a500fa3c"},"references":{"count":16,"sample":[{"doi":"","year":2019,"title":"Deep learning in remote sensing applications: A meta-analysis and review,","work_id":"043e2a1b-995e-46ae-8ddb-72923c5b40a2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Adaptive frequency enhancement network for remote sensing image semantic segmentation,","work_id":"5c6c312a-c69d-44b2-9490-10e7b88b1410","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Elevation information- guided multimodal fusion robust framework for remote sensing image segmentation,","work_id":"58710bab-7a10-478b-87c3-22906bea35bb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A multilevel multimodal fusion Transformer for remote sensing semantic segmentation,","work_id":"4c7051f1-645e-4455-b471-9c489e16c8a0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"A multisensor data fusion model for semantic segmentation in aerial images,","work_id":"58806e15-c22e-4d1c-9a7d-00c6fbc9e681","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":16,"snapshot_sha256":"ffd657ed6bf1093eb2ec7f897dd314e98ec69266f0aaa5a1f1363b2c95b0c2ff","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b6c766b83f98a355155d30dbe977afcfe83b1431065d93ca1265282b2969d0d4"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}