{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RE3H4LLU77N4NLS3TU5REAIZNM","short_pith_number":"pith:RE3H4LLU","schema_version":"1.0","canonical_sha256":"89367e2d74ffdbc6ae5b9d3b1201196b0e181402a2e6172d66197592df6e3c1d","source":{"kind":"arxiv","id":"1911.07158","version":5},"attestation_state":"computed","paper":{"title":"Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitrios Lymberopoulos, Di Wang, Fuxun Yu, Nikolaos Karianakis, Pei Yu, Sidi Lu, Tong Shen, Weisong Shi, Xiang Chen, Yinpeng Chen","submitted_at":"2019-11-17T05:59:33Z","abstract_excerpt":"Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new domains/environments without any expensive label cost. However, without ground truth labels, most prior works on UDA for object detection tasks can only perform coarse image-level and/or feature-level adaptation by using adversarial learning methods. In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the "},"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":"1911.07158","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-11-17T05:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"c9603650cef51dfbb9990f2aba1e6f4ba0d25395e6f8a70e7a1d0a576f9be6dd","abstract_canon_sha256":"535ab1b9945b503a96510c3947517d375d08ff99b13981887e90af2a0d17db89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:24.249835Z","signature_b64":"0Cu+bIoeqZn6vZO/FeOTTWMfG2VYEBGF8R4Vq0kgRh4rb0KOkY30G2Lb+2vLalDA/KpxVPAF0KvbKEFjZDM7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89367e2d74ffdbc6ae5b9d3b1201196b0e181402a2e6172d66197592df6e3c1d","last_reissued_at":"2026-07-05T03:03:24.249294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:24.249294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitrios Lymberopoulos, Di Wang, Fuxun Yu, Nikolaos Karianakis, Pei Yu, Sidi Lu, Tong Shen, Weisong Shi, Xiang Chen, Yinpeng Chen","submitted_at":"2019-11-17T05:59:33Z","abstract_excerpt":"Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new domains/environments without any expensive label cost. However, without ground truth labels, most prior works on UDA for object detection tasks can only perform coarse image-level and/or feature-level adaptation by using adversarial learning methods. In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07158","kind":"arxiv","version":5},"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/1911.07158/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":"1911.07158","created_at":"2026-07-05T03:03:24.249378+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07158v5","created_at":"2026-07-05T03:03:24.249378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07158","created_at":"2026-07-05T03:03:24.249378+00:00"},{"alias_kind":"pith_short_12","alias_value":"RE3H4LLU77N4","created_at":"2026-07-05T03:03:24.249378+00:00"},{"alias_kind":"pith_short_16","alias_value":"RE3H4LLU77N4NLS3","created_at":"2026-07-05T03:03:24.249378+00:00"},{"alias_kind":"pith_short_8","alias_value":"RE3H4LLU","created_at":"2026-07-05T03:03:24.249378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08230","citing_title":"Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM","json":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM.json","graph_json":"https://pith.science/api/pith-number/RE3H4LLU77N4NLS3TU5REAIZNM/graph.json","events_json":"https://pith.science/api/pith-number/RE3H4LLU77N4NLS3TU5REAIZNM/events.json","paper":"https://pith.science/paper/RE3H4LLU"},"agent_actions":{"view_html":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM","download_json":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM.json","view_paper":"https://pith.science/paper/RE3H4LLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07158&json=true","fetch_graph":"https://pith.science/api/pith-number/RE3H4LLU77N4NLS3TU5REAIZNM/graph.json","fetch_events":"https://pith.science/api/pith-number/RE3H4LLU77N4NLS3TU5REAIZNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM/action/storage_attestation","attest_author":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM/action/author_attestation","sign_citation":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM/action/citation_signature","submit_replication":"https://pith.science/pith/RE3H4LLU77N4NLS3TU5REAIZNM/action/replication_record"}},"created_at":"2026-07-05T03:03:24.249378+00:00","updated_at":"2026-07-05T03:03:24.249378+00:00"}