{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NHG3Z2Y4L4UVGHN4KPYO5SXT3Y","short_pith_number":"pith:NHG3Z2Y4","schema_version":"1.0","canonical_sha256":"69cdbceb1c5f29531dbc53f0eecaf3de13b6693cca1ff470376d0dda2d9a9b40","source":{"kind":"arxiv","id":"2003.00707","version":2},"attestation_state":"computed","paper":{"title":"Unbiased Mean Teacher for Cross-domain Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhong Deng, Lixin Duan, Wen Li, Yuhua Chen","submitted_at":"2020-03-02T08:20:55Z","abstract_excerpt":"Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distinctive domains. In this paper, we propose a new Unbiased Mean Teacher (UMT) model for cross-domain object detection. We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies. In particular, for the teacher model, we propose a cross-domain distillation method for MT to maxim"},"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":"2003.00707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-02T08:20:55Z","cross_cats_sorted":[],"title_canon_sha256":"d8619c4022d0ab6ede64caef563b56161400781fc722a8a8f2d069495b1889a2","abstract_canon_sha256":"aaafbc36ae8eada61a92f0c706ae707d2f1eee669a8fcb7c9a4bd088053de9de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:35.914753Z","signature_b64":"eRBZGt1pVd/ZnR7eK3BneqqVee+MR1ssshhlmdVlxgcQjCXwXUio5ABHugzqzwWBUXQjDamdXOUqJe77kdw+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69cdbceb1c5f29531dbc53f0eecaf3de13b6693cca1ff470376d0dda2d9a9b40","last_reissued_at":"2026-07-05T02:51:35.914284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:35.914284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unbiased Mean Teacher for Cross-domain Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhong Deng, Lixin Duan, Wen Li, Yuhua Chen","submitted_at":"2020-03-02T08:20:55Z","abstract_excerpt":"Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distinctive domains. In this paper, we propose a new Unbiased Mean Teacher (UMT) model for cross-domain object detection. We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies. In particular, for the teacher model, we propose a cross-domain distillation method for MT to maxim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00707","kind":"arxiv","version":2},"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/2003.00707/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":"2003.00707","created_at":"2026-07-05T02:51:35.914375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.00707v2","created_at":"2026-07-05T02:51:35.914375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00707","created_at":"2026-07-05T02:51:35.914375+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHG3Z2Y4L4UV","created_at":"2026-07-05T02:51:35.914375+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHG3Z2Y4L4UVGHN4","created_at":"2026-07-05T02:51:35.914375+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHG3Z2Y4","created_at":"2026-07-05T02:51:35.914375+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/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y","json":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y.json","graph_json":"https://pith.science/api/pith-number/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/graph.json","events_json":"https://pith.science/api/pith-number/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/events.json","paper":"https://pith.science/paper/NHG3Z2Y4"},"agent_actions":{"view_html":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y","download_json":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y.json","view_paper":"https://pith.science/paper/NHG3Z2Y4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.00707&json=true","fetch_graph":"https://pith.science/api/pith-number/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/action/storage_attestation","attest_author":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/action/author_attestation","sign_citation":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/action/citation_signature","submit_replication":"https://pith.science/pith/NHG3Z2Y4L4UVGHN4KPYO5SXT3Y/action/replication_record"}},"created_at":"2026-07-05T02:51:35.914375+00:00","updated_at":"2026-07-05T02:51:35.914375+00:00"}