{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YGP3AIT57AB4HXVVUAPI4SHPJM","short_pith_number":"pith:YGP3AIT5","schema_version":"1.0","canonical_sha256":"c19fb0227df803c3deb5a01e8e48ef4b2fb3df1584f59cb06d6ec711abbd0a3f","source":{"kind":"arxiv","id":"2402.09315","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Object Detection with Sparse Context Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hichem Sahbi, Jie Mei, Mingliang Xu, Mingyuan Jiu, Xiaoheng Jiang","submitted_at":"2024-02-14T17:10:01Z","abstract_excerpt":"Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain. However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce. In this paper, we devise a novel sparse context transformer (SCT) that effectively leverages object knowledge in the sou"},"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":"2402.09315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-14T17:10:01Z","cross_cats_sorted":[],"title_canon_sha256":"13f53f20cc9d979a1f1397ab46263b48a45fb7ed3c99dea7aff5cc6dad73307d","abstract_canon_sha256":"f53c9e576a4ee35f6a6d7bec20a48f5f9bc2db1f306106ad835b393c14ad6854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:12.032203Z","signature_b64":"lELX09xmeRwSdSSLx+DtG7mCutV6fuWjSfTfqNNohqWQ9BlpeO1d+aozfRzTrNgg/F+h1mOUldMJYCKtGDFWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c19fb0227df803c3deb5a01e8e48ef4b2fb3df1584f59cb06d6ec711abbd0a3f","last_reissued_at":"2026-07-05T07:45:12.031735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:12.031735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Object Detection with Sparse Context Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hichem Sahbi, Jie Mei, Mingliang Xu, Mingyuan Jiu, Xiaoheng Jiang","submitted_at":"2024-02-14T17:10:01Z","abstract_excerpt":"Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain. However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce. In this paper, we devise a novel sparse context transformer (SCT) that effectively leverages object knowledge in the sou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09315","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/2402.09315/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":"2402.09315","created_at":"2026-07-05T07:45:12.031793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09315v1","created_at":"2026-07-05T07:45:12.031793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09315","created_at":"2026-07-05T07:45:12.031793+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGP3AIT57AB4","created_at":"2026-07-05T07:45:12.031793+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGP3AIT57AB4HXVV","created_at":"2026-07-05T07:45:12.031793+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGP3AIT5","created_at":"2026-07-05T07:45:12.031793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01412","citing_title":"Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM","json":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM.json","graph_json":"https://pith.science/api/pith-number/YGP3AIT57AB4HXVVUAPI4SHPJM/graph.json","events_json":"https://pith.science/api/pith-number/YGP3AIT57AB4HXVVUAPI4SHPJM/events.json","paper":"https://pith.science/paper/YGP3AIT5"},"agent_actions":{"view_html":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM","download_json":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM.json","view_paper":"https://pith.science/paper/YGP3AIT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09315&json=true","fetch_graph":"https://pith.science/api/pith-number/YGP3AIT57AB4HXVVUAPI4SHPJM/graph.json","fetch_events":"https://pith.science/api/pith-number/YGP3AIT57AB4HXVVUAPI4SHPJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM/action/storage_attestation","attest_author":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM/action/author_attestation","sign_citation":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM/action/citation_signature","submit_replication":"https://pith.science/pith/YGP3AIT57AB4HXVVUAPI4SHPJM/action/replication_record"}},"created_at":"2026-07-05T07:45:12.031793+00:00","updated_at":"2026-07-05T07:45:12.031793+00:00"}