{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F462MGINCQNWXSUCVLX7CWFULP","short_pith_number":"pith:F462MGIN","schema_version":"1.0","canonical_sha256":"2f3da6190d141b6bca82aaeff158b45bee00dd1a8be03aa3e579ee5057396488","source":{"kind":"arxiv","id":"2410.21708","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Hao Zhang, Pan Zhou, Peng-Tao Jiang, Ruihao Xia, Yang Tang, Yu Liang","submitted_at":"2024-10-29T03:49:40Z","abstract_excerpt":"Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation hinders their performance and restricts their application in real-world multimodal scenarios. To address this issue, we propose Modality Adaptation with text-to-image Diffusion Models (MADM) for semantic segmentation task which utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities"},"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":"2410.21708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T03:49:40Z","cross_cats_sorted":[],"title_canon_sha256":"87827df6de2363514f0fe037607abdbf09c6e7d6d0c4846d9cdc0a21caeaa466","abstract_canon_sha256":"61f3ba33ca58c745bced22cfdb331bd38c6f36f94952a41337fd83eb54a2be7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:32.091736Z","signature_b64":"pifRSkQJeYG3chieGCZYwMWLbWP4iJjpvJECa4htOHRxC8Dd8pzZ/AVo9bDGI9RQ7WUm4Y1Df/utAAuKnsBJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f3da6190d141b6bca82aaeff158b45bee00dd1a8be03aa3e579ee5057396488","last_reissued_at":"2026-07-05T09:27:32.091253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:32.091253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Hao Zhang, Pan Zhou, Peng-Tao Jiang, Ruihao Xia, Yang Tang, Yu Liang","submitted_at":"2024-10-29T03:49:40Z","abstract_excerpt":"Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation hinders their performance and restricts their application in real-world multimodal scenarios. To address this issue, we propose Modality Adaptation with text-to-image Diffusion Models (MADM) for semantic segmentation task which utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21708","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/2410.21708/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":"2410.21708","created_at":"2026-07-05T09:27:32.091321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21708v1","created_at":"2026-07-05T09:27:32.091321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21708","created_at":"2026-07-05T09:27:32.091321+00:00"},{"alias_kind":"pith_short_12","alias_value":"F462MGINCQNW","created_at":"2026-07-05T09:27:32.091321+00:00"},{"alias_kind":"pith_short_16","alias_value":"F462MGINCQNWXSUC","created_at":"2026-07-05T09:27:32.091321+00:00"},{"alias_kind":"pith_short_8","alias_value":"F462MGIN","created_at":"2026-07-05T09:27:32.091321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP","json":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP.json","graph_json":"https://pith.science/api/pith-number/F462MGINCQNWXSUCVLX7CWFULP/graph.json","events_json":"https://pith.science/api/pith-number/F462MGINCQNWXSUCVLX7CWFULP/events.json","paper":"https://pith.science/paper/F462MGIN"},"agent_actions":{"view_html":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP","download_json":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP.json","view_paper":"https://pith.science/paper/F462MGIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21708&json=true","fetch_graph":"https://pith.science/api/pith-number/F462MGINCQNWXSUCVLX7CWFULP/graph.json","fetch_events":"https://pith.science/api/pith-number/F462MGINCQNWXSUCVLX7CWFULP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP/action/storage_attestation","attest_author":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP/action/author_attestation","sign_citation":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP/action/citation_signature","submit_replication":"https://pith.science/pith/F462MGINCQNWXSUCVLX7CWFULP/action/replication_record"}},"created_at":"2026-07-05T09:27:32.091321+00:00","updated_at":"2026-07-05T09:27:32.091321+00:00"}