{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VMCUWKME4BBYFQWUYKC6FN6DSO","short_pith_number":"pith:VMCUWKME","schema_version":"1.0","canonical_sha256":"ab054b2984e04382c2d4c285e2b7c393b3584d4d47f168e581939cf8cab51b18","source":{"kind":"arxiv","id":"2402.03094","version":4},"attestation_state":"computed","paper":{"title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lian Huai, Luc Van Gool, Tong Liu, Xingqun Jiang, Xingyu Qiu, Yanwei Fu, Yixuan Pan, Yuqian Fu, Yu Wang, Zeyu Shangguan","submitted_at":"2024-02-05T15:25:32Z","abstract_excerpt":"This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, their generalization to CD-FSOD remains unclear: 1) can such open-set detection methods easily generalize to CD-FSOD? 2) If not, how can models be enhanced when facing huge domain gaps? To answer the first question, we employ measures including style, inter-class variance (ICV), and indefinable boundarie"},"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":"2402.03094","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-05T15:25:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2ae0dda35ae8f733fd1bc94f12e6e7b2c03c3933de295d8bdb5cec46bf170506","abstract_canon_sha256":"53a1dfe077df94295528b50822d79958a405c14174c347af20077a8f54ad96ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:25.548787Z","signature_b64":"5H/4gYHVkQFdTE+Tr/fpMoWD+rqV7R8hkpel6jqI7U56A/cZP15S/n77LKUCKiMu3Ag7JIcdLBISgIHJAcmCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab054b2984e04382c2d4c285e2b7c393b3584d4d47f168e581939cf8cab51b18","last_reissued_at":"2026-07-05T09:12:25.548255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:25.548255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lian Huai, Luc Van Gool, Tong Liu, Xingqun Jiang, Xingyu Qiu, Yanwei Fu, Yixuan Pan, Yuqian Fu, Yu Wang, Zeyu Shangguan","submitted_at":"2024-02-05T15:25:32Z","abstract_excerpt":"This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, their generalization to CD-FSOD remains unclear: 1) can such open-set detection methods easily generalize to CD-FSOD? 2) If not, how can models be enhanced when facing huge domain gaps? To answer the first question, we employ measures including style, inter-class variance (ICV), and indefinable boundarie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03094","kind":"arxiv","version":4},"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/2402.03094/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":"2402.03094","created_at":"2026-07-05T09:12:25.548321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03094v4","created_at":"2026-07-05T09:12:25.548321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03094","created_at":"2026-07-05T09:12:25.548321+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMCUWKME4BBY","created_at":"2026-07-05T09:12:25.548321+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMCUWKME4BBYFQWU","created_at":"2026-07-05T09:12:25.548321+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMCUWKME","created_at":"2026-07-05T09:12:25.548321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16749","citing_title":"AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO","json":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO.json","graph_json":"https://pith.science/api/pith-number/VMCUWKME4BBYFQWUYKC6FN6DSO/graph.json","events_json":"https://pith.science/api/pith-number/VMCUWKME4BBYFQWUYKC6FN6DSO/events.json","paper":"https://pith.science/paper/VMCUWKME"},"agent_actions":{"view_html":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO","download_json":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO.json","view_paper":"https://pith.science/paper/VMCUWKME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03094&json=true","fetch_graph":"https://pith.science/api/pith-number/VMCUWKME4BBYFQWUYKC6FN6DSO/graph.json","fetch_events":"https://pith.science/api/pith-number/VMCUWKME4BBYFQWUYKC6FN6DSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO/action/storage_attestation","attest_author":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO/action/author_attestation","sign_citation":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO/action/citation_signature","submit_replication":"https://pith.science/pith/VMCUWKME4BBYFQWUYKC6FN6DSO/action/replication_record"}},"created_at":"2026-07-05T09:12:25.548321+00:00","updated_at":"2026-07-05T09:12:25.548321+00:00"}