{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JKG5L2NYH3FSMYAMZT6GAGRGW6","short_pith_number":"pith:JKG5L2NY","schema_version":"1.0","canonical_sha256":"4a8dd5e9b83ecb26600cccfc601a26b794ef40dce71fac28048d394237a9ad11","source":{"kind":"arxiv","id":"2005.03819","version":1},"attestation_state":"computed","paper":{"title":"One-Shot Object Detection without Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Lin Zhang, Xiang Li, Yau Pun Chen, Yu-Wing Tai","submitted_at":"2020-05-08T01:59:23Z","abstract_excerpt":"Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited. In this paper, we attempt to enrich such categories by addressing the one-shot object detection problem, where the number of annotated training examples for learning an unseen class is limited to one. We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module, the combination of which integrates metric learning with an anchor-free Faster R-CNN-style detection pipeline, eventually e"},"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":"2005.03819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-08T01:59:23Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"a811835e0fcfcc14130007de969b58cb0ab9c88907afcd0925cc921993d73fef","abstract_canon_sha256":"a284c34efb44e727f01f6aaadccb47118fbef694d60554ffb563a70947d65d71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:26.413919Z","signature_b64":"VNqZd1RzBCEsPBdJU4FULa2NKUROggWi3LZE6PUnkKTx1BjafG9iG0qQgdMmIKLjUCgPQpC4GwMbjXx6L8caAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a8dd5e9b83ecb26600cccfc601a26b794ef40dce71fac28048d394237a9ad11","last_reissued_at":"2026-07-05T01:01:26.413521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:26.413521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Shot Object Detection without Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Lin Zhang, Xiang Li, Yau Pun Chen, Yu-Wing Tai","submitted_at":"2020-05-08T01:59:23Z","abstract_excerpt":"Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited. In this paper, we attempt to enrich such categories by addressing the one-shot object detection problem, where the number of annotated training examples for learning an unseen class is limited to one. We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module, the combination of which integrates metric learning with an anchor-free Faster R-CNN-style detection pipeline, eventually e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03819","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/2005.03819/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":"2005.03819","created_at":"2026-07-05T01:01:26.413582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.03819v1","created_at":"2026-07-05T01:01:26.413582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03819","created_at":"2026-07-05T01:01:26.413582+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKG5L2NYH3FS","created_at":"2026-07-05T01:01:26.413582+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKG5L2NYH3FSMYAM","created_at":"2026-07-05T01:01:26.413582+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKG5L2NY","created_at":"2026-07-05T01:01:26.413582+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/JKG5L2NYH3FSMYAMZT6GAGRGW6","json":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6.json","graph_json":"https://pith.science/api/pith-number/JKG5L2NYH3FSMYAMZT6GAGRGW6/graph.json","events_json":"https://pith.science/api/pith-number/JKG5L2NYH3FSMYAMZT6GAGRGW6/events.json","paper":"https://pith.science/paper/JKG5L2NY"},"agent_actions":{"view_html":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6","download_json":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6.json","view_paper":"https://pith.science/paper/JKG5L2NY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.03819&json=true","fetch_graph":"https://pith.science/api/pith-number/JKG5L2NYH3FSMYAMZT6GAGRGW6/graph.json","fetch_events":"https://pith.science/api/pith-number/JKG5L2NYH3FSMYAMZT6GAGRGW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6/action/storage_attestation","attest_author":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6/action/author_attestation","sign_citation":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6/action/citation_signature","submit_replication":"https://pith.science/pith/JKG5L2NYH3FSMYAMZT6GAGRGW6/action/replication_record"}},"created_at":"2026-07-05T01:01:26.413582+00:00","updated_at":"2026-07-05T01:01:26.413582+00:00"}