{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LQLBVD6X7VCMBNP6UHAIORQP2Z","short_pith_number":"pith:LQLBVD6X","schema_version":"1.0","canonical_sha256":"5c161a8fd7fd44c0b5fea1c087460fd65322bd19e71667cce4db7fa49a86fa51","source":{"kind":"arxiv","id":"2407.00851","version":1},"attestation_state":"computed","paper":{"title":"SAFE: a SAR Feature Extractor based on self-supervised learning and masked Siamese ViTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chengfang Ren, Jean-Philippe Ovarlez, Joana Frontera-Pons, Max Muzeau","submitted_at":"2024-06-30T23:11:20Z","abstract_excerpt":"Due to its all-weather and day-and-night capabilities, Synthetic Aperture Radar imagery is essential for various applications such as disaster management, earth monitoring, change detection and target recognition. However, the scarcity of labeled SAR data limits the performance of most deep learning algorithms. To address this issue, we propose a novel self-supervised learning framework based on masked Siamese Vision Transformers to create a General SAR Feature Extractor coined SAFE. Our method leverages contrastive learning principles to train a model on unlabeled SAR data, extracting robust "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.00851","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T23:11:20Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"2cd72f6af73e17dcfb8325b8e0c9d1f21fcc0cae4c45611a98252cf241ec7afc","abstract_canon_sha256":"34dcf8f0e89761755d98b57bf4fe7711333f3ca935ab9a7d1ebe63c573c81090"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:25.480050Z","signature_b64":"uZ+oXu+8TnoeMGNVq/8xN3shAXcB8/sw0c45C1cJEcEoApgc0h3Rv6hDvRFPreuJ5z8YRC1AggDNqOEWo5pMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c161a8fd7fd44c0b5fea1c087460fd65322bd19e71667cce4db7fa49a86fa51","last_reissued_at":"2026-07-05T08:38:25.479047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:25.479047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAFE: a SAR Feature Extractor based on self-supervised learning and masked Siamese ViTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chengfang Ren, Jean-Philippe Ovarlez, Joana Frontera-Pons, Max Muzeau","submitted_at":"2024-06-30T23:11:20Z","abstract_excerpt":"Due to its all-weather and day-and-night capabilities, Synthetic Aperture Radar imagery is essential for various applications such as disaster management, earth monitoring, change detection and target recognition. However, the scarcity of labeled SAR data limits the performance of most deep learning algorithms. To address this issue, we propose a novel self-supervised learning framework based on masked Siamese Vision Transformers to create a General SAR Feature Extractor coined SAFE. Our method leverages contrastive learning principles to train a model on unlabeled SAR data, extracting robust "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00851","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.00851/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.00851","created_at":"2026-07-05T08:38:25.479115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00851v1","created_at":"2026-07-05T08:38:25.479115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00851","created_at":"2026-07-05T08:38:25.479115+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQLBVD6X7VCM","created_at":"2026-07-05T08:38:25.479115+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQLBVD6X7VCMBNP6","created_at":"2026-07-05T08:38:25.479115+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQLBVD6X","created_at":"2026-07-05T08:38:25.479115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.11999","citing_title":"A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z","json":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z.json","graph_json":"https://pith.science/api/pith-number/LQLBVD6X7VCMBNP6UHAIORQP2Z/graph.json","events_json":"https://pith.science/api/pith-number/LQLBVD6X7VCMBNP6UHAIORQP2Z/events.json","paper":"https://pith.science/paper/LQLBVD6X"},"agent_actions":{"view_html":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z","download_json":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z.json","view_paper":"https://pith.science/paper/LQLBVD6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00851&json=true","fetch_graph":"https://pith.science/api/pith-number/LQLBVD6X7VCMBNP6UHAIORQP2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/LQLBVD6X7VCMBNP6UHAIORQP2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z/action/storage_attestation","attest_author":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z/action/author_attestation","sign_citation":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z/action/citation_signature","submit_replication":"https://pith.science/pith/LQLBVD6X7VCMBNP6UHAIORQP2Z/action/replication_record"}},"created_at":"2026-07-05T08:38:25.479115+00:00","updated_at":"2026-07-05T08:38:25.479115+00:00"}