{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:55W2JQTUHTXQRLIOKMJHETEA5N","short_pith_number":"pith:55W2JQTU","schema_version":"1.0","canonical_sha256":"ef6da4c2743cef08ad0e5312724c80eb6de88352899046cd2fb64efbe5f7390e","source":{"kind":"arxiv","id":"2112.05749","version":2},"attestation_state":"computed","paper":{"title":"Label, Verify, Correct: A Simple Few Shot Object Detection Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Prannay Kaul, Weidi Xie","submitted_at":"2021-12-10T18:59:06Z","abstract_excerpt":"The objective of this paper is few-shot object detection (FSOD) -- the task of expanding an object detector for a new category given only a few instances for training. We introduce a simple pseudo-labelling method to source high-quality pseudo-annotations from the training set, for each new category, vastly increasing the number of training instances and reducing class imbalance; our method finds previously unlabelled instances. Na\\\"ively training with model predictions yields sub-optimal performance; we present two novel methods to improve the precision of the pseudo-labelling process: first,"},"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":"2112.05749","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T18:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"f0c7d7c76269269e96a194cf26f4d2d36e30b5afc215a2705a97ba368b19ae12","abstract_canon_sha256":"f53f63284744deb36b35091fbc8d6f4128b0ece9eb10b2d3a114638fae2f0f99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:17.347138Z","signature_b64":"Eq27dicW5yfxBPBkij7N1AieH7VH+0Xoj4ktwEL96+GeLv1dNCmJs1ZoW9vUzJiA3K4BLxG5bykS9ufUihtIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef6da4c2743cef08ad0e5312724c80eb6de88352899046cd2fb64efbe5f7390e","last_reissued_at":"2026-07-05T04:09:17.346639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:17.346639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label, Verify, Correct: A Simple Few Shot Object Detection Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Prannay Kaul, Weidi Xie","submitted_at":"2021-12-10T18:59:06Z","abstract_excerpt":"The objective of this paper is few-shot object detection (FSOD) -- the task of expanding an object detector for a new category given only a few instances for training. We introduce a simple pseudo-labelling method to source high-quality pseudo-annotations from the training set, for each new category, vastly increasing the number of training instances and reducing class imbalance; our method finds previously unlabelled instances. Na\\\"ively training with model predictions yields sub-optimal performance; we present two novel methods to improve the precision of the pseudo-labelling process: first,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05749","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/2112.05749/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":"2112.05749","created_at":"2026-07-05T04:09:17.346704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.05749v2","created_at":"2026-07-05T04:09:17.346704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05749","created_at":"2026-07-05T04:09:17.346704+00:00"},{"alias_kind":"pith_short_12","alias_value":"55W2JQTUHTXQ","created_at":"2026-07-05T04:09:17.346704+00:00"},{"alias_kind":"pith_short_16","alias_value":"55W2JQTUHTXQRLIO","created_at":"2026-07-05T04:09:17.346704+00:00"},{"alias_kind":"pith_short_8","alias_value":"55W2JQTU","created_at":"2026-07-05T04:09:17.346704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09083","citing_title":"BakuFlow: A Streamlining Semi-Automatic Label Generation Tool","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N","json":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N.json","graph_json":"https://pith.science/api/pith-number/55W2JQTUHTXQRLIOKMJHETEA5N/graph.json","events_json":"https://pith.science/api/pith-number/55W2JQTUHTXQRLIOKMJHETEA5N/events.json","paper":"https://pith.science/paper/55W2JQTU"},"agent_actions":{"view_html":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N","download_json":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N.json","view_paper":"https://pith.science/paper/55W2JQTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.05749&json=true","fetch_graph":"https://pith.science/api/pith-number/55W2JQTUHTXQRLIOKMJHETEA5N/graph.json","fetch_events":"https://pith.science/api/pith-number/55W2JQTUHTXQRLIOKMJHETEA5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N/action/storage_attestation","attest_author":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N/action/author_attestation","sign_citation":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N/action/citation_signature","submit_replication":"https://pith.science/pith/55W2JQTUHTXQRLIOKMJHETEA5N/action/replication_record"}},"created_at":"2026-07-05T04:09:17.346704+00:00","updated_at":"2026-07-05T04:09:17.346704+00:00"}