{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7WPB63W4MTU7VL4S2CXJRA2KM2","short_pith_number":"pith:7WPB63W4","schema_version":"1.0","canonical_sha256":"fd9e1f6edc64e9faaf92d0ae98834a669d2f48814506db552ba427de4439b936","source":{"kind":"arxiv","id":"2312.17243","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Universal Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dantong Niu, Long Lian, Roei Herzig, Trevor Darrell, Xinyang Han, Xudong Wang","submitted_at":"2023-12-28T18:59:04Z","abstract_excerpt":"Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic instance segmentation (e.g., CutLER), but not both (i.e., panoptic segmentation). We propose an Unsupervised Universal Segmentation model (U2Seg) adept at performing various image segmentation tasks -- instance, semantic and panoptic -- using a novel unified framework. U2Seg generates pseudo semantic labels for these segmentation tasks via leveraging self-supe"},"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":"2312.17243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T18:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"018ed82f7909db9a87cb81351d79e03a69e8b42ba7242a9d0655124de8e027b5","abstract_canon_sha256":"2e0f3b8c216cefa47b7e42d29a84406374d0a11b8e3bc82e8c947209986ad71e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:41.311301Z","signature_b64":"JFn/xasU1RAAozf/h+s2aKgE/aE0V6tY1Ek/UcUrfpzZBh6aD3qwKHGl3FcsOTBmVvBZKXL7DSHK9NRcUVEdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd9e1f6edc64e9faaf92d0ae98834a669d2f48814506db552ba427de4439b936","last_reissued_at":"2026-07-05T07:28:41.310796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:41.310796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Universal Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dantong Niu, Long Lian, Roei Herzig, Trevor Darrell, Xinyang Han, Xudong Wang","submitted_at":"2023-12-28T18:59:04Z","abstract_excerpt":"Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic instance segmentation (e.g., CutLER), but not both (i.e., panoptic segmentation). We propose an Unsupervised Universal Segmentation model (U2Seg) adept at performing various image segmentation tasks -- instance, semantic and panoptic -- using a novel unified framework. U2Seg generates pseudo semantic labels for these segmentation tasks via leveraging self-supe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17243","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/2312.17243/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":"2312.17243","created_at":"2026-07-05T07:28:41.310853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17243v1","created_at":"2026-07-05T07:28:41.310853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17243","created_at":"2026-07-05T07:28:41.310853+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WPB63W4MTU7","created_at":"2026-07-05T07:28:41.310853+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WPB63W4MTU7VL4S","created_at":"2026-07-05T07:28:41.310853+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WPB63W4","created_at":"2026-07-05T07:28:41.310853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10775","citing_title":"Spatially Selective Self-Training for Unsupervised Building Change Detection","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2","json":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2.json","graph_json":"https://pith.science/api/pith-number/7WPB63W4MTU7VL4S2CXJRA2KM2/graph.json","events_json":"https://pith.science/api/pith-number/7WPB63W4MTU7VL4S2CXJRA2KM2/events.json","paper":"https://pith.science/paper/7WPB63W4"},"agent_actions":{"view_html":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2","download_json":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2.json","view_paper":"https://pith.science/paper/7WPB63W4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17243&json=true","fetch_graph":"https://pith.science/api/pith-number/7WPB63W4MTU7VL4S2CXJRA2KM2/graph.json","fetch_events":"https://pith.science/api/pith-number/7WPB63W4MTU7VL4S2CXJRA2KM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2/action/storage_attestation","attest_author":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2/action/author_attestation","sign_citation":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2/action/citation_signature","submit_replication":"https://pith.science/pith/7WPB63W4MTU7VL4S2CXJRA2KM2/action/replication_record"}},"created_at":"2026-07-05T07:28:41.310853+00:00","updated_at":"2026-07-05T07:28:41.310853+00:00"}