{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2DYNLW2QAUSLJBBRX3LFLDZRWS","short_pith_number":"pith:2DYNLW2Q","schema_version":"1.0","canonical_sha256":"d0f0d5db500524b48431bed6558f31b4a1e85cf85266008fc09290e5f07256e4","source":{"kind":"arxiv","id":"2208.14662","version":1},"attestation_state":"computed","paper":{"title":"AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Schwung, Maximilian Menke, Thomas Wenzel","submitted_at":"2022-08-31T07:20:25Z","abstract_excerpt":"Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice. Typically, additional data sources are utilized to support the training task. In these, however, domain gaps between different data sources pose a challenge in deep learning. GAN-based image-to-image style-transfer is commonly applied to shrink the domain gap, but is unstable and decoupled from the object detection task. We propose AWADA, an Attention-Weighted Adversarial Domain Adaptation framework for creating a feedback loop between style-"},"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":"2208.14662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-31T07:20:25Z","cross_cats_sorted":[],"title_canon_sha256":"cb2c4cda71563a419c56fd69a3392b283c5ec1af565dad39feb90c27b32fc31a","abstract_canon_sha256":"9fdd3ddceafa1863fc5aadd0f3e3306ecb290adf1de249c83bfb32b145bd8f3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:32.842244Z","signature_b64":"cZapQ6w3jHFWcPfGDVEfSP5xbSKplhC6zEPHMc0KfKkZsCs/xzS/x90FFKifthSoENKGFQ64Mzbi/b5vafCDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0f0d5db500524b48431bed6558f31b4a1e85cf85266008fc09290e5f07256e4","last_reissued_at":"2026-07-05T04:53:32.841872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:32.841872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Schwung, Maximilian Menke, Thomas Wenzel","submitted_at":"2022-08-31T07:20:25Z","abstract_excerpt":"Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice. Typically, additional data sources are utilized to support the training task. In these, however, domain gaps between different data sources pose a challenge in deep learning. GAN-based image-to-image style-transfer is commonly applied to shrink the domain gap, but is unstable and decoupled from the object detection task. We propose AWADA, an Attention-Weighted Adversarial Domain Adaptation framework for creating a feedback loop between style-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14662","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/2208.14662/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":"2208.14662","created_at":"2026-07-05T04:53:32.841939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.14662v1","created_at":"2026-07-05T04:53:32.841939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14662","created_at":"2026-07-05T04:53:32.841939+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DYNLW2QAUSL","created_at":"2026-07-05T04:53:32.841939+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DYNLW2QAUSLJBBR","created_at":"2026-07-05T04:53:32.841939+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DYNLW2Q","created_at":"2026-07-05T04:53:32.841939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02294","citing_title":"Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS","json":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS.json","graph_json":"https://pith.science/api/pith-number/2DYNLW2QAUSLJBBRX3LFLDZRWS/graph.json","events_json":"https://pith.science/api/pith-number/2DYNLW2QAUSLJBBRX3LFLDZRWS/events.json","paper":"https://pith.science/paper/2DYNLW2Q"},"agent_actions":{"view_html":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS","download_json":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS.json","view_paper":"https://pith.science/paper/2DYNLW2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.14662&json=true","fetch_graph":"https://pith.science/api/pith-number/2DYNLW2QAUSLJBBRX3LFLDZRWS/graph.json","fetch_events":"https://pith.science/api/pith-number/2DYNLW2QAUSLJBBRX3LFLDZRWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS/action/storage_attestation","attest_author":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS/action/author_attestation","sign_citation":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS/action/citation_signature","submit_replication":"https://pith.science/pith/2DYNLW2QAUSLJBBRX3LFLDZRWS/action/replication_record"}},"created_at":"2026-07-05T04:53:32.841939+00:00","updated_at":"2026-07-05T04:53:32.841939+00:00"}