{"paper":{"title":"TERRA-CD: Multi-Temporal Framework for Multi-class and Semantic Change Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TERRA-CD supplies 5221 Sentinel-2 image pairs across 232 cities with three annotation layers for land-cover and change detection.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Omkar Oak, Rujuta Budke, Rukmini Nazre, Suraj Sawant","submitted_at":"2026-05-14T10:08:51Z","abstract_excerpt":"Urban vegetation monitoring plays a vital role in understanding environmental changes, yet comprehensive datasets for this purpose remain limited. To address this gap, we present the Temporal Remote-sensing Repository for Analyzing Change Detection (TERRA-CD), a benchmark dataset comprising 5,221 Sentinel-2 image pairs from 2019 and 2024, covering 232 cities across the USA and Europe. The dataset features three distinct annotation schemes: 4-class land cover mapping masks, 3-class vegetation change masks, and 13-class semantic change masks capturing all possible land cover transitions. Using v"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we present the Temporal Remote-sensing Repository for Analyzing Change Detection (TERRA-CD), a benchmark dataset comprising 5,221 Sentinel-2 image pairs from 2019 and 2024, covering 232 cities across the USA and Europe. The dataset features three distinct annotation schemes: 4-class land cover mapping masks, 3-class vegetation change masks, and 13-class semantic change masks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The chosen 232 cities and the 2019-2024 time window are assumed to be sufficiently representative for general urban vegetation and semantic change detection tasks; the quality and consistency of the three annotation schemes are also taken as given without detailed validation statistics in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TERRA-CD is a new multi-temporal Sentinel-2 dataset with three levels of change-detection annotations that benchmarks Siamese networks, STANet, Bi-SRNet, and other models for multi-class and semantic change detection.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TERRA-CD supplies 5221 Sentinel-2 image pairs across 232 cities with three annotation layers for land-cover and change detection.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7d01229d90b96654eee0e8551f25f68b5e145c047a3a98432b4b4bf67f6682f2"},"source":{"id":"2605.14651","kind":"arxiv","version":1},"verdict":{"id":"83a9ad42-db65-4ffa-9c25-21337405788c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:29:01.640433Z","strongest_claim":"we present the Temporal Remote-sensing Repository for Analyzing Change Detection (TERRA-CD), a benchmark dataset comprising 5,221 Sentinel-2 image pairs from 2019 and 2024, covering 232 cities across the USA and Europe. The dataset features three distinct annotation schemes: 4-class land cover mapping masks, 3-class vegetation change masks, and 13-class semantic change masks.","one_line_summary":"TERRA-CD is a new multi-temporal Sentinel-2 dataset with three levels of change-detection annotations that benchmarks Siamese networks, STANet, Bi-SRNet, and other models for multi-class and semantic change detection.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The chosen 232 cities and the 2019-2024 time window are assumed to be sufficiently representative for general urban vegetation and semantic change detection tasks; the quality and consistency of the three annotation schemes are also taken as given without detailed validation statistics in the abstract.","pith_extraction_headline":"TERRA-CD supplies 5221 Sentinel-2 image pairs across 232 cities with three annotation layers for land-cover and change detection."},"references":{"count":27,"sample":[{"doi":"","year":2020,"title":"Chen, H. & Shi, Z. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection.Remote Sensing.12pp. 1662 (2020)","work_id":"13addb0c-a1e9-4ca4-87ff-f4350f8f571b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Adriano, B., Yokoya, N., Xia, J., Miura, H., Liu, W. & Matsuoka, M. Learning from multimodal and multitemporal earth observation data for building damage mapping. ISPRS Journal Of Photogrammetry And R","work_id":"8141ab31-0c1d-499a-b9b4-9dc7a292476a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Daudt, R., Le Saux, B., Boulch, A. & Gousseau, Y. Multitask learning for large- scale semantic change detection.Computer Vision And Image Understanding.187 pp. 102783 (2019)","work_id":"a1c75814-0a2c-4424-be2e-d4ad147b586b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Yang, K., Xia, G., Liu, Z., Du, B., Yang, W., Pelillo, M. & Zhang, L. Asymmetric siamese networks for semantic change detection in aerial images.IEEE Transactions On Geoscience And Remote Sensing.60pp","work_id":"ae22f022-9f24-4c13-a8ae-0321d839bbba","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Zhu, Q., Guo, X., Li, Z. & Li, D. A review of multi-class change detection for satellite remote sensing imagery.Geo-spatial Information Science.27, 1-15 (2024)","work_id":"2953369a-ac0d-490e-b6ce-dfcd8603cfd3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":27,"snapshot_sha256":"09908bbd60b41b2bc6f3ed94c15e1eaaa469e24b8d8562c94aab99544eeb76aa","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}