{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/score-scene-context-matters-in-open","title":"SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation","arxiv_id":"2507.12857","date":"2025-07-17","proceeding":null,"authors":["Shiqi Huang","Shuting He","Huaiyuan Qin","Bihan Wen"],"abstract":"Most existing remote sensing instance segmentation approaches are designed for close-vocabulary prediction, limiting their ability to recognize novel categories or generalize across datasets. This restricts their applicability in diverse Earth observation scenarios. To address this, we introduce open-vocabulary (OV) learning for remote sensing instance segmentation. While current OV segmentation models perform well on natural image datasets, their direct application to remote sensing faces challenges such as diverse landscapes, seasonal variations, and the presence of small or ambiguous objects in aerial imagery. To overcome these challenges, we propose $\\textbf{SCORE}$ ($\\textbf{S}$cene $\\textbf{C}$ontext matters in $\\textbf{O}$pen-vocabulary $\\textbf{RE}$mote sensing instance segmentation), a framework that integrates multi-granularity scene context, i.e., regional context and global context, to enhance both visual and textual representations. Specifically, we introduce Region-Aware Integration, which refines class embeddings with regional context to improve object distinguishability. Additionally, we propose Global Context Adaptation, which enriches naive text embeddings with remote sensing global context, creating a more adaptable and expressive linguistic latent space for the classifier. We establish new benchmarks for OV remote sensing instance segmentation across diverse datasets. Experimental results demonstrate that, our proposed method achieves SOTA performance, which provides a robust solution for large-scale, real-world geospatial analysis. Our code is available at https://github.com/HuangShiqi128/SCORE.","url_abs":"https://arxiv.org/abs/2507.12857v1","url_pdf":"https://arxiv.org/pdf/2507.12857v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"earth-observation","task_name":"Earth Observation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2507.12857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.12857"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/HuangShiqi128/SCORE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"found_in_text":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bc2cb481a75c370d","entry":"batch_dice_loss","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/modeling/matcher.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/modeling/matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"code_sha256_prefix":"1edd24985036b0bf","entry":"batch_sigmoid_ce_loss","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/modeling/matcher.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/modeling/matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1edd24985036b0bf"}},{"code_sha256_prefix":"ff38c0c0ab1871da","entry":"bbox_overlaps","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/evaluation/ins_seg_evaluation_gzero_utils/bbox_overlaps.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/evaluation/ins_seg_evaluation_gzero_utils/bbox_overlaps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ff38c0c0ab1871da"}},{"code_sha256_prefix":"2dcb8123d89bb1ff","entry":"calculate_uncertainty","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/modeling/criterion.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/modeling/criterion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2dcb8123d89bb1ff"}},{"code_sha256_prefix":"89f75e54ff128be0","entry":"dice_loss","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/modeling/criterion.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/modeling/criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"89f75e54ff128be0"}},{"code_sha256_prefix":"58cc9ff3bf75e753","entry":"nested_tensor_from_tensor_list","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/utils/misc.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/utils/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"58cc9ff3bf75e753"}},{"code_sha256_prefix":"e41f7604e432c210","entry":"set_recall_param","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/evaluation/ins_seg_evaluation_gzero_utils/recall.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/evaluation/ins_seg_evaluation_gzero_utils/recall.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e41f7604e432c210"}},{"code_sha256_prefix":"d0c61e8dba511aa3","entry":"sigmoid_ce_loss","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/modeling/criterion.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/modeling/criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0c61e8dba511aa3"}},{"code_sha256_prefix":"141b13358e6b0894","entry":"xyxy2xywh","repo":"HuangShiqi128/SCORE","repo_kind":"found_in_text","path":"score/evaluation/ins_seg_evaluation_gzero_utils/coco_utils.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/evaluation/ins_seg_evaluation_gzero_utils/coco_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"141b13358e6b0894"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}