{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YGEEZDLJTA5FADO6D3BIWXW7Y6","short_pith_number":"pith:YGEEZDLJ","schema_version":"1.0","canonical_sha256":"c1884c8d69983a500dde1ec28b5edfc79e8e8b1f94bf4e8a93e784761b251756","source":{"kind":"arxiv","id":"2302.09779","version":1},"attestation_state":"computed","paper":{"title":"Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jong-Hwan Kim, Tae-Min Choi","submitted_at":"2023-02-20T05:48:46Z","abstract_excerpt":"In this paper, we explore incremental few-shot object detection (iFSD), which incrementally learns novel classes using only a few examples without revisiting base classes. Previous iFSD works achieved the desired results by applying meta-learning. However, meta-learning approaches show insufficient performance that is difficult to apply to practical problems. In this light, we propose a simple fine-tuning-based approach, the Incremental Two-stage Fine-tuning Approach (iTFA) for iFSD, which contains three steps: 1) base training using abundant base classes with the class-agnostic box regressor,"},"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":"2302.09779","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-20T05:48:46Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"09d68532c0735fe3a94cef76a57a1fde4884370cda13aad35099b73fe49a51cd","abstract_canon_sha256":"8fbc34dc6a3ece11dee33af6ebe81fc3891bb7398a8d3f437f467e249e766ab7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:47.233470Z","signature_b64":"7ZYROyl4aRSs0CXnTxdOtwN/1Fva9EWh12zNMjEsuB9QDMPh2B11EZ2fFjZQ32J9wyyr/tSamgYwcLE9AIo7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1884c8d69983a500dde1ec28b5edfc79e8e8b1f94bf4e8a93e784761b251756","last_reissued_at":"2026-07-05T06:41:47.232979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:47.232979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jong-Hwan Kim, Tae-Min Choi","submitted_at":"2023-02-20T05:48:46Z","abstract_excerpt":"In this paper, we explore incremental few-shot object detection (iFSD), which incrementally learns novel classes using only a few examples without revisiting base classes. Previous iFSD works achieved the desired results by applying meta-learning. However, meta-learning approaches show insufficient performance that is difficult to apply to practical problems. In this light, we propose a simple fine-tuning-based approach, the Incremental Two-stage Fine-tuning Approach (iTFA) for iFSD, which contains three steps: 1) base training using abundant base classes with the class-agnostic box regressor,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09779","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/2302.09779/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":"2302.09779","created_at":"2026-07-05T06:41:47.233037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09779v1","created_at":"2026-07-05T06:41:47.233037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09779","created_at":"2026-07-05T06:41:47.233037+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGEEZDLJTA5F","created_at":"2026-07-05T06:41:47.233037+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGEEZDLJTA5FADO6","created_at":"2026-07-05T06:41:47.233037+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGEEZDLJ","created_at":"2026-07-05T06:41:47.233037+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/YGEEZDLJTA5FADO6D3BIWXW7Y6","json":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6.json","graph_json":"https://pith.science/api/pith-number/YGEEZDLJTA5FADO6D3BIWXW7Y6/graph.json","events_json":"https://pith.science/api/pith-number/YGEEZDLJTA5FADO6D3BIWXW7Y6/events.json","paper":"https://pith.science/paper/YGEEZDLJ"},"agent_actions":{"view_html":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6","download_json":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6.json","view_paper":"https://pith.science/paper/YGEEZDLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09779&json=true","fetch_graph":"https://pith.science/api/pith-number/YGEEZDLJTA5FADO6D3BIWXW7Y6/graph.json","fetch_events":"https://pith.science/api/pith-number/YGEEZDLJTA5FADO6D3BIWXW7Y6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6/action/storage_attestation","attest_author":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6/action/author_attestation","sign_citation":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6/action/citation_signature","submit_replication":"https://pith.science/pith/YGEEZDLJTA5FADO6D3BIWXW7Y6/action/replication_record"}},"created_at":"2026-07-05T06:41:47.233037+00:00","updated_at":"2026-07-05T06:41:47.233037+00:00"}