{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2I23ZK7UD3SYTID3X4T3QD5CPL","short_pith_number":"pith:2I23ZK7U","schema_version":"1.0","canonical_sha256":"d235bcabf41ee589a07bbf27b80fa27acafc0b2ff88be6129b4ebff7cbead97c","source":{"kind":"arxiv","id":"2404.04469","version":1},"attestation_state":"computed","paper":{"title":"Mixed-Query Transformer: A Unified Image Segmentation Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashwin Swaminathan, Hao Yang, Pei Wang, R. Manmatha, Stefano Soatto, Zhaowei Cai","submitted_at":"2024-04-06T01:54:17Z","abstract_excerpt":"Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task. In this paper, we introduce the Mixed-Query Transformer (MQ-Former), a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights. To enable this, we propose a mixed query strategy, which can effectively and dynamically accommodate different types of objects without heuristic designs. In addition, the unified arch"},"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":"2404.04469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-06T01:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"2d894a0316f9e10baffc128845dc89f3c0be56082610c2958f830882698acb2d","abstract_canon_sha256":"afed0e005ffac6502e5f932c865b30c73ef090efead82451bbfbc9cb5bf67111"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:17.159937Z","signature_b64":"3BTLHmeP06OjrGzmRkMzFkuuvn0Hb7HqViJ23iiaaxaX0hGtakZL4vZg6vCn/Q/xn8rBydGg9uTSwuWNlxunCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d235bcabf41ee589a07bbf27b80fa27acafc0b2ff88be6129b4ebff7cbead97c","last_reissued_at":"2026-07-05T08:05:17.159583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:17.159583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixed-Query Transformer: A Unified Image Segmentation Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashwin Swaminathan, Hao Yang, Pei Wang, R. Manmatha, Stefano Soatto, Zhaowei Cai","submitted_at":"2024-04-06T01:54:17Z","abstract_excerpt":"Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task. In this paper, we introduce the Mixed-Query Transformer (MQ-Former), a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights. To enable this, we propose a mixed query strategy, which can effectively and dynamically accommodate different types of objects without heuristic designs. In addition, the unified arch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04469","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/2404.04469/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":"2404.04469","created_at":"2026-07-05T08:05:17.159643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04469v1","created_at":"2026-07-05T08:05:17.159643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04469","created_at":"2026-07-05T08:05:17.159643+00:00"},{"alias_kind":"pith_short_12","alias_value":"2I23ZK7UD3SY","created_at":"2026-07-05T08:05:17.159643+00:00"},{"alias_kind":"pith_short_16","alias_value":"2I23ZK7UD3SYTID3","created_at":"2026-07-05T08:05:17.159643+00:00"},{"alias_kind":"pith_short_8","alias_value":"2I23ZK7U","created_at":"2026-07-05T08:05:17.159643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14587","citing_title":"Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL","json":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL.json","graph_json":"https://pith.science/api/pith-number/2I23ZK7UD3SYTID3X4T3QD5CPL/graph.json","events_json":"https://pith.science/api/pith-number/2I23ZK7UD3SYTID3X4T3QD5CPL/events.json","paper":"https://pith.science/paper/2I23ZK7U"},"agent_actions":{"view_html":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL","download_json":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL.json","view_paper":"https://pith.science/paper/2I23ZK7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04469&json=true","fetch_graph":"https://pith.science/api/pith-number/2I23ZK7UD3SYTID3X4T3QD5CPL/graph.json","fetch_events":"https://pith.science/api/pith-number/2I23ZK7UD3SYTID3X4T3QD5CPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL/action/storage_attestation","attest_author":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL/action/author_attestation","sign_citation":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL/action/citation_signature","submit_replication":"https://pith.science/pith/2I23ZK7UD3SYTID3X4T3QD5CPL/action/replication_record"}},"created_at":"2026-07-05T08:05:17.159643+00:00","updated_at":"2026-07-05T08:05:17.159643+00:00"}