{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YMVGJYWL3S33M4VIAUONZGWB5J","short_pith_number":"pith:YMVGJYWL","schema_version":"1.0","canonical_sha256":"c32a64e2cbdcb7b672a8051cdc9ac1ea72338a99573a1dadf3d744df0f158372","source":{"kind":"arxiv","id":"2403.13652","version":2},"attestation_state":"computed","paper":{"title":"ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atsuto Maki, Hiroki Azuma, Yusuke Matsui","submitted_at":"2024-03-20T14:58:09Z","abstract_excerpt":"Deep learning models achieve high accuracy in segmentation tasks among others, yet domain shift often degrades the models' performance, which can be critical in real-world scenarios where no target images are available. This paper proposes a zero-shot domain adaptation method based on diffusion models, called ZoDi, which is two-fold by the design: zero-shot image transfer and model adaptation. First, we utilize an off-the-shelf diffusion model to synthesize target-like images by transferring the domain of source images to the target domain. In this we specifically try to maintain the layout an"},"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":"2403.13652","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T14:58:09Z","cross_cats_sorted":[],"title_canon_sha256":"e7d2fc3630aa37c2e2a2c323784c0984784843370df20fe39fc9f607a9960ae6","abstract_canon_sha256":"5577d54e94ea185e2c31152829f1d84f1aa2eb6ff10e442fab9ee4225a0a1cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:25.141108Z","signature_b64":"w6f6+zfas5976vMPBD+LlW2pCPaYFY3CXBRMySGfDUw/O/szoaEBCaM1ex2OTMnESxfT8GYMVA2XWBO1ggERCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c32a64e2cbdcb7b672a8051cdc9ac1ea72338a99573a1dadf3d744df0f158372","last_reissued_at":"2026-07-05T09:11:25.140621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:25.140621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atsuto Maki, Hiroki Azuma, Yusuke Matsui","submitted_at":"2024-03-20T14:58:09Z","abstract_excerpt":"Deep learning models achieve high accuracy in segmentation tasks among others, yet domain shift often degrades the models' performance, which can be critical in real-world scenarios where no target images are available. This paper proposes a zero-shot domain adaptation method based on diffusion models, called ZoDi, which is two-fold by the design: zero-shot image transfer and model adaptation. First, we utilize an off-the-shelf diffusion model to synthesize target-like images by transferring the domain of source images to the target domain. In this we specifically try to maintain the layout an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13652","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/2403.13652/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":"2403.13652","created_at":"2026-07-05T09:11:25.140680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13652v2","created_at":"2026-07-05T09:11:25.140680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13652","created_at":"2026-07-05T09:11:25.140680+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMVGJYWL3S33","created_at":"2026-07-05T09:11:25.140680+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMVGJYWL3S33M4VI","created_at":"2026-07-05T09:11:25.140680+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMVGJYWL","created_at":"2026-07-05T09:11:25.140680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00777","citing_title":"IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J","json":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J.json","graph_json":"https://pith.science/api/pith-number/YMVGJYWL3S33M4VIAUONZGWB5J/graph.json","events_json":"https://pith.science/api/pith-number/YMVGJYWL3S33M4VIAUONZGWB5J/events.json","paper":"https://pith.science/paper/YMVGJYWL"},"agent_actions":{"view_html":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J","download_json":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J.json","view_paper":"https://pith.science/paper/YMVGJYWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13652&json=true","fetch_graph":"https://pith.science/api/pith-number/YMVGJYWL3S33M4VIAUONZGWB5J/graph.json","fetch_events":"https://pith.science/api/pith-number/YMVGJYWL3S33M4VIAUONZGWB5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J/action/storage_attestation","attest_author":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J/action/author_attestation","sign_citation":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J/action/citation_signature","submit_replication":"https://pith.science/pith/YMVGJYWL3S33M4VIAUONZGWB5J/action/replication_record"}},"created_at":"2026-07-05T09:11:25.140680+00:00","updated_at":"2026-07-05T09:11:25.140680+00:00"}