{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GDB4HVCXM3BVGEOZDU7UMCF4Z7","short_pith_number":"pith:GDB4HVCX","schema_version":"1.0","canonical_sha256":"30c3c3d45766c35311d91d3f4608bccfd8291e7cf35824193591a03bef866c74","source":{"kind":"arxiv","id":"2405.01217","version":3},"attestation_state":"computed","paper":{"title":"CromSS: Cross-modal pre-training with noisy labels for remote sensing image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenying Liu, Conrad Albrecht, Xiao Xiang Zhu, Yi Wang","submitted_at":"2024-05-02T11:58:06Z","abstract_excerpt":"We explore the potential of large-scale noisily labeled data to enhance feature learning by pretraining semantic segmentation models within a multi-modal framework for geospatial applications. We propose a novel Cross-modal Sample Selection (CromSS) method, a weakly supervised pretraining strategy designed to improve feature representations through cross-modal consistency and noise mitigation techniques. Unlike conventional pretraining approaches, CromSS exploits massive amounts of noisy and easy-to-come-by labels for improved feature learning beneficial to semantic segmentation tasks. We inve"},"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":"2405.01217","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T11:58:06Z","cross_cats_sorted":[],"title_canon_sha256":"6e47cb28374b2c98ea844a44184ef4b77cd42194e642fdeb6d7318c57252ae0c","abstract_canon_sha256":"36d20db89771af4ba088912e70d1ac08cf9d158210023a3c24efc198a14c43d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:26.547431Z","signature_b64":"bnV5iKHlyy66gE0TkXOcwryUSb3Ic+u4d7+kw/Z3aZku65dqw2+Jpvf3rA+PK2GZSdmyflwNuczpsE/cWQd+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30c3c3d45766c35311d91d3f4608bccfd8291e7cf35824193591a03bef866c74","last_reissued_at":"2026-07-05T10:32:26.546767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:26.546767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CromSS: Cross-modal pre-training with noisy labels for remote sensing image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenying Liu, Conrad Albrecht, Xiao Xiang Zhu, Yi Wang","submitted_at":"2024-05-02T11:58:06Z","abstract_excerpt":"We explore the potential of large-scale noisily labeled data to enhance feature learning by pretraining semantic segmentation models within a multi-modal framework for geospatial applications. We propose a novel Cross-modal Sample Selection (CromSS) method, a weakly supervised pretraining strategy designed to improve feature representations through cross-modal consistency and noise mitigation techniques. Unlike conventional pretraining approaches, CromSS exploits massive amounts of noisy and easy-to-come-by labels for improved feature learning beneficial to semantic segmentation tasks. We inve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01217","kind":"arxiv","version":3},"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/2405.01217/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":"2405.01217","created_at":"2026-07-05T10:32:26.546852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01217v3","created_at":"2026-07-05T10:32:26.546852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01217","created_at":"2026-07-05T10:32:26.546852+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDB4HVCXM3BV","created_at":"2026-07-05T10:32:26.546852+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDB4HVCXM3BVGEOZ","created_at":"2026-07-05T10:32:26.546852+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDB4HVCX","created_at":"2026-07-05T10:32:26.546852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7","json":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7.json","graph_json":"https://pith.science/api/pith-number/GDB4HVCXM3BVGEOZDU7UMCF4Z7/graph.json","events_json":"https://pith.science/api/pith-number/GDB4HVCXM3BVGEOZDU7UMCF4Z7/events.json","paper":"https://pith.science/paper/GDB4HVCX"},"agent_actions":{"view_html":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7","download_json":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7.json","view_paper":"https://pith.science/paper/GDB4HVCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01217&json=true","fetch_graph":"https://pith.science/api/pith-number/GDB4HVCXM3BVGEOZDU7UMCF4Z7/graph.json","fetch_events":"https://pith.science/api/pith-number/GDB4HVCXM3BVGEOZDU7UMCF4Z7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7/action/storage_attestation","attest_author":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7/action/author_attestation","sign_citation":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7/action/citation_signature","submit_replication":"https://pith.science/pith/GDB4HVCXM3BVGEOZDU7UMCF4Z7/action/replication_record"}},"created_at":"2026-07-05T10:32:26.546852+00:00","updated_at":"2026-07-05T10:32:26.546852+00:00"}