{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SUJQIJ3OM6THFNAA7T4AZOFZM7","short_pith_number":"pith:SUJQIJ3O","schema_version":"1.0","canonical_sha256":"951304276e67a672b400fcf80cb8b967cb92e80cfa681ea99ed267cf63390ed2","source":{"kind":"arxiv","id":"2003.06957","version":1},"attestation_state":"computed","paper":{"title":"Frustratingly Simple Few-Shot Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fisher Yu, Joseph E. Gonzalez, Thomas E. Huang, Trevor Darrell, Xin Wang","submitted_at":"2020-03-16T00:29:14Z","abstract_excerpt":"Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the eva"},"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":"2003.06957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-16T00:29:14Z","cross_cats_sorted":[],"title_canon_sha256":"59549b0c28269ddc6bee050221c82a006a77214f12d1672b38d7cbccfa2dc713","abstract_canon_sha256":"f5a13ee63e6f8d8792fe208841a53bb28ac50565d4506481286567203223d7e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:48:08.179673Z","signature_b64":"d2OytlSI3iw1Q5J61Udekvn6kEwBmNGIUt/TQhf/nx2R/Rb/8yti57dDKkmCkp4K1blXL4ko7GPqWz+YyQ+LBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"951304276e67a672b400fcf80cb8b967cb92e80cfa681ea99ed267cf63390ed2","last_reissued_at":"2026-07-05T00:48:08.179103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:48:08.179103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frustratingly Simple Few-Shot Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fisher Yu, Joseph E. Gonzalez, Thomas E. Huang, Trevor Darrell, Xin Wang","submitted_at":"2020-03-16T00:29:14Z","abstract_excerpt":"Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06957","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/2003.06957/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":"2003.06957","created_at":"2026-07-05T00:48:08.179178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06957v1","created_at":"2026-07-05T00:48:08.179178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06957","created_at":"2026-07-05T00:48:08.179178+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUJQIJ3OM6TH","created_at":"2026-07-05T00:48:08.179178+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUJQIJ3OM6THFNAA","created_at":"2026-07-05T00:48:08.179178+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUJQIJ3O","created_at":"2026-07-05T00:48:08.179178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23069","citing_title":"Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19817","citing_title":"Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09245","citing_title":"Proposal Refinement for Few-Shot Object Detection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23069","citing_title":"Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29539","citing_title":"GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02905","citing_title":"UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11998","citing_title":"The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results","ref_index":113,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7","json":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7.json","graph_json":"https://pith.science/api/pith-number/SUJQIJ3OM6THFNAA7T4AZOFZM7/graph.json","events_json":"https://pith.science/api/pith-number/SUJQIJ3OM6THFNAA7T4AZOFZM7/events.json","paper":"https://pith.science/paper/SUJQIJ3O"},"agent_actions":{"view_html":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7","download_json":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7.json","view_paper":"https://pith.science/paper/SUJQIJ3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06957&json=true","fetch_graph":"https://pith.science/api/pith-number/SUJQIJ3OM6THFNAA7T4AZOFZM7/graph.json","fetch_events":"https://pith.science/api/pith-number/SUJQIJ3OM6THFNAA7T4AZOFZM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7/action/storage_attestation","attest_author":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7/action/author_attestation","sign_citation":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7/action/citation_signature","submit_replication":"https://pith.science/pith/SUJQIJ3OM6THFNAA7T4AZOFZM7/action/replication_record"}},"created_at":"2026-07-05T00:48:08.179178+00:00","updated_at":"2026-07-05T00:48:08.179178+00:00"}