{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DHJ7APMSBATB6OOZXNXDE4P3WB","short_pith_number":"pith:DHJ7APMS","schema_version":"1.0","canonical_sha256":"19d3f03d9208261f39d9bb6e3271fbb046dcd9ab2a031f8a0594a9481cdfd68d","source":{"kind":"arxiv","id":"2201.05869","version":2},"attestation_state":"computed","paper":{"title":"Prototype Guided Network for Anomaly Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaoyun An, Yi Jin, Yiqing Hao","submitted_at":"2022-01-15T15:07:38Z","abstract_excerpt":"Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomaly probability for pixels. In this paper, a Prototype Guided Anomaly segmentation Network (PGAN) is proposed to extract semantic prototypes for in-distribution training data from limited annotated images. In the model, prototypes are used to model the hierarchical category semantic information and distinguish OOD pixels. The proposed PGAN model incl"},"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":"2201.05869","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-15T15:07:38Z","cross_cats_sorted":[],"title_canon_sha256":"d7543542a85e509b97138f4c1468961e452c9e53e6212d32716574cdf87a68f1","abstract_canon_sha256":"c46de420b60afc1efcda391c073edb475ec1a8b0dc87f5ecfd3c293c4dee1123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:16.283410Z","signature_b64":"kt/bDSMq6A3p4fhF2/OEv4m8O8vY9Gne7GfkBzJpBXwS9puofUSrYBmhCnzca3syhotcUs28D6gmFeDqXyhzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d3f03d9208261f39d9bb6e3271fbb046dcd9ab2a031f8a0594a9481cdfd68d","last_reissued_at":"2026-07-05T04:05:16.283054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:16.283054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototype Guided Network for Anomaly Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaoyun An, Yi Jin, Yiqing Hao","submitted_at":"2022-01-15T15:07:38Z","abstract_excerpt":"Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomaly probability for pixels. In this paper, a Prototype Guided Anomaly segmentation Network (PGAN) is proposed to extract semantic prototypes for in-distribution training data from limited annotated images. In the model, prototypes are used to model the hierarchical category semantic information and distinguish OOD pixels. The proposed PGAN model incl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05869","kind":"arxiv","version":2},"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/2201.05869/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":"2201.05869","created_at":"2026-07-05T04:05:16.283108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05869v2","created_at":"2026-07-05T04:05:16.283108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05869","created_at":"2026-07-05T04:05:16.283108+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHJ7APMSBATB","created_at":"2026-07-05T04:05:16.283108+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHJ7APMSBATB6OOZ","created_at":"2026-07-05T04:05:16.283108+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHJ7APMS","created_at":"2026-07-05T04:05:16.283108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16467","citing_title":"Cross-Domain Semantic Segmentation with Large Language Model-Assisted Descriptor Generation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB","json":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB.json","graph_json":"https://pith.science/api/pith-number/DHJ7APMSBATB6OOZXNXDE4P3WB/graph.json","events_json":"https://pith.science/api/pith-number/DHJ7APMSBATB6OOZXNXDE4P3WB/events.json","paper":"https://pith.science/paper/DHJ7APMS"},"agent_actions":{"view_html":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB","download_json":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB.json","view_paper":"https://pith.science/paper/DHJ7APMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05869&json=true","fetch_graph":"https://pith.science/api/pith-number/DHJ7APMSBATB6OOZXNXDE4P3WB/graph.json","fetch_events":"https://pith.science/api/pith-number/DHJ7APMSBATB6OOZXNXDE4P3WB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB/action/storage_attestation","attest_author":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB/action/author_attestation","sign_citation":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB/action/citation_signature","submit_replication":"https://pith.science/pith/DHJ7APMSBATB6OOZXNXDE4P3WB/action/replication_record"}},"created_at":"2026-07-05T04:05:16.283108+00:00","updated_at":"2026-07-05T04:05:16.283108+00:00"}