{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GPZ2K24TROKESW7N4S5MFC3OMW","short_pith_number":"pith:GPZ2K24T","schema_version":"1.0","canonical_sha256":"33f3a56b938b94495bede4bac28b6e65828c5712cdda860afdc50fdda8b8f61f","source":{"kind":"arxiv","id":"1911.02559","version":3},"attestation_state":"computed","paper":{"title":"SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Harsh Maheshwari, Marios Savvides, Weichen Yao, Zhiqiang Shen","submitted_at":"2019-11-06T18:59:01Z","abstract_excerpt":"Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is label-agnostic and the feature distributions between training and testing domains are dissimilar or even totally different. In this paper, we propose a gradient detach based stacked complementary losses (SCL) method that uses detection losses as the primary objective, and cuts in several auxiliary losses in different network stages accompanying with gradient detach tra"},"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":"1911.02559","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-06T18:59:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"49a5d67b5521e51777c661600d457af6381f34037dc3d684a9a01342e9bcc655","abstract_canon_sha256":"cdabd1bd9aa47793aff00491b5097c5a169f89310ce48e6f9117bd12af9183c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:56.161495Z","signature_b64":"32G671FLA2ALUH1C2kCTqi6kGzZO+/LjKaBEbkrC3EBoFUCyG3iZ/0EveHbfMmyQKK+FxX82n7D6ZmCjvQOwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f3a56b938b94495bede4bac28b6e65828c5712cdda860afdc50fdda8b8f61f","last_reissued_at":"2026-07-05T00:20:56.161024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:56.161024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Harsh Maheshwari, Marios Savvides, Weichen Yao, Zhiqiang Shen","submitted_at":"2019-11-06T18:59:01Z","abstract_excerpt":"Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is label-agnostic and the feature distributions between training and testing domains are dissimilar or even totally different. In this paper, we propose a gradient detach based stacked complementary losses (SCL) method that uses detection losses as the primary objective, and cuts in several auxiliary losses in different network stages accompanying with gradient detach tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02559","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.02559/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":"1911.02559","created_at":"2026-07-05T00:20:56.161074+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.02559v3","created_at":"2026-07-05T00:20:56.161074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02559","created_at":"2026-07-05T00:20:56.161074+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPZ2K24TROKE","created_at":"2026-07-05T00:20:56.161074+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPZ2K24TROKESW7N","created_at":"2026-07-05T00:20:56.161074+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPZ2K24T","created_at":"2026-07-05T00:20:56.161074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00608","citing_title":"De-Simplifying Pseudo Labels to Enhancing Domain Adaptive Object Detection","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW","json":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW.json","graph_json":"https://pith.science/api/pith-number/GPZ2K24TROKESW7N4S5MFC3OMW/graph.json","events_json":"https://pith.science/api/pith-number/GPZ2K24TROKESW7N4S5MFC3OMW/events.json","paper":"https://pith.science/paper/GPZ2K24T"},"agent_actions":{"view_html":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW","download_json":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW.json","view_paper":"https://pith.science/paper/GPZ2K24T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.02559&json=true","fetch_graph":"https://pith.science/api/pith-number/GPZ2K24TROKESW7N4S5MFC3OMW/graph.json","fetch_events":"https://pith.science/api/pith-number/GPZ2K24TROKESW7N4S5MFC3OMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW/action/storage_attestation","attest_author":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW/action/author_attestation","sign_citation":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW/action/citation_signature","submit_replication":"https://pith.science/pith/GPZ2K24TROKESW7N4S5MFC3OMW/action/replication_record"}},"created_at":"2026-07-05T00:20:56.161074+00:00","updated_at":"2026-07-05T00:20:56.161074+00:00"}