{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZW2GF2FK7VVGUBIEG7YEMFJGCO","short_pith_number":"pith:ZW2GF2FK","schema_version":"1.0","canonical_sha256":"cdb462e8aafd6a6a050437f04615261390296c20cbef9347558634d13dfd8edc","source":{"kind":"arxiv","id":"2410.09004","version":1},"attestation_state":"computed","paper":{"title":"DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hantao Yao, Haochen Li, Ling Li, Rui Zhang, Xiaqing Li, Xinkai Song, Xin Zhang, Yifan Hao, Yongwei Zhao, Yunji Chen","submitted_at":"2024-10-11T17:20:04Z","abstract_excerpt":"Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlabelled domain, i.e., domain-specific knowledge of the target domain. To solve the issue, we propose a novel"},"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":"2410.09004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-11T17:20:04Z","cross_cats_sorted":[],"title_canon_sha256":"1a71e05f20814cb7761cdd76c87af8f76022c3dee8984804503ff5da85f7d531","abstract_canon_sha256":"fc53763901b6c97e7c9005cae45c451fffea5d6600f61ac40c61e951b8c058a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:20.597481Z","signature_b64":"yir1+Z7HlSNRYvCDVQ+XplAuQknDGgfUtZ+0KiHw9xXR2PeTPmytDx6sEr701fOrhsQfsKr/187h4HjpSN8JCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdb462e8aafd6a6a050437f04615261390296c20cbef9347558634d13dfd8edc","last_reissued_at":"2026-07-05T09:19:20.596988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:20.596988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hantao Yao, Haochen Li, Ling Li, Rui Zhang, Xiaqing Li, Xinkai Song, Xin Zhang, Yifan Hao, Yongwei Zhao, Yunji Chen","submitted_at":"2024-10-11T17:20:04Z","abstract_excerpt":"Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlabelled domain, i.e., domain-specific knowledge of the target domain. To solve the issue, we propose a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09004","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/2410.09004/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":"2410.09004","created_at":"2026-07-05T09:19:20.597046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09004v1","created_at":"2026-07-05T09:19:20.597046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09004","created_at":"2026-07-05T09:19:20.597046+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZW2GF2FK7VVG","created_at":"2026-07-05T09:19:20.597046+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZW2GF2FK7VVGUBIE","created_at":"2026-07-05T09:19:20.597046+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZW2GF2FK","created_at":"2026-07-05T09:19:20.597046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07051","citing_title":"YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO","json":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO.json","graph_json":"https://pith.science/api/pith-number/ZW2GF2FK7VVGUBIEG7YEMFJGCO/graph.json","events_json":"https://pith.science/api/pith-number/ZW2GF2FK7VVGUBIEG7YEMFJGCO/events.json","paper":"https://pith.science/paper/ZW2GF2FK"},"agent_actions":{"view_html":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO","download_json":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO.json","view_paper":"https://pith.science/paper/ZW2GF2FK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09004&json=true","fetch_graph":"https://pith.science/api/pith-number/ZW2GF2FK7VVGUBIEG7YEMFJGCO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZW2GF2FK7VVGUBIEG7YEMFJGCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO/action/storage_attestation","attest_author":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO/action/author_attestation","sign_citation":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO/action/citation_signature","submit_replication":"https://pith.science/pith/ZW2GF2FK7VVGUBIEG7YEMFJGCO/action/replication_record"}},"created_at":"2026-07-05T09:19:20.597046+00:00","updated_at":"2026-07-05T09:19:20.597046+00:00"}