{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2M3G4NT3W6PEGD66ITIL4DRZFZ","short_pith_number":"pith:2M3G4NT3","schema_version":"1.0","canonical_sha256":"d3366e367bb79e430fde44d0be0e392e5af164cec78692b45844eed60503eb28","source":{"kind":"arxiv","id":"2303.11681","version":4},"attestation_state":"computed","paper":{"title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hong Zhou, Mike Zheng Shou, Weijia Wu, Yuzhong Zhao","submitted_at":"2023-03-21T08:43:15Z","abstract_excerpt":"Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is possible to automatically obtain accurate semantic masks of synthetic images generated by the Off-the-shelf Stable Diffusion model, which uses only text-image pairs during training. Our approach, called DiffuMask, exploits the potential of the cross-attention map between text and image, which is natural and seamless to extend the text-driven image synthesis to sem"},"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":"2303.11681","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-21T08:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"354e352c29e5a555b73ae408663b079ebd39c51c7829bda4254714c74bbc6fa8","abstract_canon_sha256":"d45513a412f8593c2a3f7c1dfa55f55b63bbafdbbb7d74f4f5e68ce75e88841e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:36.563946Z","signature_b64":"tUcdXec5p5ScgJDVxD/HiROv0Szei99Nz9YfYIHdUTnGcfTpLJRAewCmzftALIJP3kzFxbBi7IKSCr0MR2g+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3366e367bb79e430fde44d0be0e392e5af164cec78692b45844eed60503eb28","last_reissued_at":"2026-07-05T07:35:36.563515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:36.563515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hong Zhou, Mike Zheng Shou, Weijia Wu, Yuzhong Zhao","submitted_at":"2023-03-21T08:43:15Z","abstract_excerpt":"Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is possible to automatically obtain accurate semantic masks of synthetic images generated by the Off-the-shelf Stable Diffusion model, which uses only text-image pairs during training. Our approach, called DiffuMask, exploits the potential of the cross-attention map between text and image, which is natural and seamless to extend the text-driven image synthesis to sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11681","kind":"arxiv","version":4},"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/2303.11681/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":"2303.11681","created_at":"2026-07-05T07:35:36.563573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11681v4","created_at":"2026-07-05T07:35:36.563573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11681","created_at":"2026-07-05T07:35:36.563573+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M3G4NT3W6PE","created_at":"2026-07-05T07:35:36.563573+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M3G4NT3W6PEGD66","created_at":"2026-07-05T07:35:36.563573+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M3G4NT3","created_at":"2026-07-05T07:35:36.563573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07723","citing_title":"Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ","json":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ.json","graph_json":"https://pith.science/api/pith-number/2M3G4NT3W6PEGD66ITIL4DRZFZ/graph.json","events_json":"https://pith.science/api/pith-number/2M3G4NT3W6PEGD66ITIL4DRZFZ/events.json","paper":"https://pith.science/paper/2M3G4NT3"},"agent_actions":{"view_html":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ","download_json":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ.json","view_paper":"https://pith.science/paper/2M3G4NT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11681&json=true","fetch_graph":"https://pith.science/api/pith-number/2M3G4NT3W6PEGD66ITIL4DRZFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2M3G4NT3W6PEGD66ITIL4DRZFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ/action/storage_attestation","attest_author":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ/action/author_attestation","sign_citation":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ/action/citation_signature","submit_replication":"https://pith.science/pith/2M3G4NT3W6PEGD66ITIL4DRZFZ/action/replication_record"}},"created_at":"2026-07-05T07:35:36.563573+00:00","updated_at":"2026-07-05T07:35:36.563573+00:00"}