{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BPSJHRIH47FLUSU5YX2FQOI6U4","short_pith_number":"pith:BPSJHRIH","schema_version":"1.0","canonical_sha256":"0be493c507e7caba4a9dc5f458391ea7391f76cac22d970100d89d14d664c8eb","source":{"kind":"arxiv","id":"2309.13042","version":2},"attestation_state":"computed","paper":{"title":"MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Jiahao Xie, Wei Li, Xiangtai Li, Yew Soon Ong, Ziwei Liu","submitted_at":"2023-09-22T17:59:42Z","abstract_excerpt":"We present MosaicFusion, a simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation. Our method is training-free and does not rely on any label supervision. Two key designs enable us to employ an off-the-shelf text-to-image diffusion model as a useful dataset generator for object instances and mask annotations. First, we divide an image canvas into several regions and perform a single round of diffusion process to generate multiple instances simultaneously, conditioning on different text prompts. Second, we obtain corresponding instance masks b"},"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":"2309.13042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-22T17:59:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"77930bfb742083ef95811ed65bff256e82bff2f1c883215e88c19b85b861196d","abstract_canon_sha256":"7aba4365cf56e57bc67444633ab4c18f60d11b84ca714e061162d642ab838436"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:26.912357Z","signature_b64":"y8j6vvdLhGJ9mm5euym46LnLO2uqpbtoJfe1Km+C9gtDNmqm6PqGGymkeb1K3ajRDa+SOHaTQ2AANcIEPE+zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0be493c507e7caba4a9dc5f458391ea7391f76cac22d970100d89d14d664c8eb","last_reissued_at":"2026-07-05T09:15:26.911928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:26.911928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Jiahao Xie, Wei Li, Xiangtai Li, Yew Soon Ong, Ziwei Liu","submitted_at":"2023-09-22T17:59:42Z","abstract_excerpt":"We present MosaicFusion, a simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation. Our method is training-free and does not rely on any label supervision. Two key designs enable us to employ an off-the-shelf text-to-image diffusion model as a useful dataset generator for object instances and mask annotations. First, we divide an image canvas into several regions and perform a single round of diffusion process to generate multiple instances simultaneously, conditioning on different text prompts. Second, we obtain corresponding instance masks b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13042","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/2309.13042/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":"2309.13042","created_at":"2026-07-05T09:15:26.911982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13042v2","created_at":"2026-07-05T09:15:26.911982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13042","created_at":"2026-07-05T09:15:26.911982+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPSJHRIH47FL","created_at":"2026-07-05T09:15:26.911982+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPSJHRIH47FLUSU5","created_at":"2026-07-05T09:15:26.911982+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPSJHRIH","created_at":"2026-07-05T09:15:26.911982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08960","citing_title":"A Comprehensive Survey on Imbalanced Data Learning","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4","json":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4.json","graph_json":"https://pith.science/api/pith-number/BPSJHRIH47FLUSU5YX2FQOI6U4/graph.json","events_json":"https://pith.science/api/pith-number/BPSJHRIH47FLUSU5YX2FQOI6U4/events.json","paper":"https://pith.science/paper/BPSJHRIH"},"agent_actions":{"view_html":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4","download_json":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4.json","view_paper":"https://pith.science/paper/BPSJHRIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13042&json=true","fetch_graph":"https://pith.science/api/pith-number/BPSJHRIH47FLUSU5YX2FQOI6U4/graph.json","fetch_events":"https://pith.science/api/pith-number/BPSJHRIH47FLUSU5YX2FQOI6U4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4/action/storage_attestation","attest_author":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4/action/author_attestation","sign_citation":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4/action/citation_signature","submit_replication":"https://pith.science/pith/BPSJHRIH47FLUSU5YX2FQOI6U4/action/replication_record"}},"created_at":"2026-07-05T09:15:26.911982+00:00","updated_at":"2026-07-05T09:15:26.911982+00:00"}