{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MHIX4FF3ZQZQ6JGT65WSND56SW","short_pith_number":"pith:MHIX4FF3","schema_version":"1.0","canonical_sha256":"61d17e14bbcc330f24d3f76d268fbe958d78bf43ee645a4aea47db466a26e0f9","source":{"kind":"arxiv","id":"1812.04798","version":3},"attestation_state":"computed","paper":{"title":"Strong-Weak Distribution Alignment for Adaptive Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Kuniaki Saito, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2018-12-12T04:02:38Z","abstract_excerpt":"We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source and target images using an adversarial loss have been proven effective for adapting object classifiers. However, for object detection, fully matching the entire distributions of source and target images to each other at the global image level may fail, as domains could have distinct scene layouts and different combinations of objects. On the other hand, stro"},"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":"1812.04798","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-12T04:02:38Z","cross_cats_sorted":[],"title_canon_sha256":"ac14e3c17f30639c6b9f470e540390fc10073d53335fdc658477c556ff0b80f6","abstract_canon_sha256":"b134c835c23721329b92f004d5599bcd7a8cc2bc32001ee8ba79e3e8a773e8c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:14.813003Z","signature_b64":"89r438DQohWMw0e/hAW7yf0xI/v14szBGTBlf5rZHpHGyQIcaiFc4jglm2Nh0aWA4rvWBMlPR+biqQSKcvevDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d17e14bbcc330f24d3f76d268fbe958d78bf43ee645a4aea47db466a26e0f9","last_reissued_at":"2026-05-17T23:49:14.812256Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:14.812256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strong-Weak Distribution Alignment for Adaptive Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Kuniaki Saito, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2018-12-12T04:02:38Z","abstract_excerpt":"We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source and target images using an adversarial loss have been proven effective for adapting object classifiers. However, for object detection, fully matching the entire distributions of source and target images to each other at the global image level may fail, as domains could have distinct scene layouts and different combinations of objects. On the other hand, stro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04798","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1812.04798","created_at":"2026-05-17T23:49:14.812394+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.04798v3","created_at":"2026-05-17T23:49:14.812394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04798","created_at":"2026-05-17T23:49:14.812394+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHIX4FF3ZQZQ","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHIX4FF3ZQZQ6JGT","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHIX4FF3","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW","json":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW.json","graph_json":"https://pith.science/api/pith-number/MHIX4FF3ZQZQ6JGT65WSND56SW/graph.json","events_json":"https://pith.science/api/pith-number/MHIX4FF3ZQZQ6JGT65WSND56SW/events.json","paper":"https://pith.science/paper/MHIX4FF3"},"agent_actions":{"view_html":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW","download_json":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW.json","view_paper":"https://pith.science/paper/MHIX4FF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.04798&json=true","fetch_graph":"https://pith.science/api/pith-number/MHIX4FF3ZQZQ6JGT65WSND56SW/graph.json","fetch_events":"https://pith.science/api/pith-number/MHIX4FF3ZQZQ6JGT65WSND56SW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW/action/storage_attestation","attest_author":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW/action/author_attestation","sign_citation":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW/action/citation_signature","submit_replication":"https://pith.science/pith/MHIX4FF3ZQZQ6JGT65WSND56SW/action/replication_record"}},"created_at":"2026-05-17T23:49:14.812394+00:00","updated_at":"2026-05-17T23:49:14.812394+00:00"}