{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AWJXGFDBB6P7HB2LRC7ZFMUMEH","short_pith_number":"pith:AWJXGFDB","schema_version":"1.0","canonical_sha256":"05937314610f9ff3874b88bf92b28c21dea544a6e25d19af57c1236c800a27b4","source":{"kind":"arxiv","id":"2212.07671","version":2},"attestation_state":"computed","paper":{"title":"Multi-task Fusion for Efficient Panoptic-Part Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Ren\\'e Schuster, Sravan Kumar Jagadeesh","submitted_at":"2022-12-15T09:04:45Z","abstract_excerpt":"In this paper, we introduce a novel network that generates semantic, instance, and part segmentation using a shared encoder and effectively fuses them to achieve panoptic-part segmentation. Unifying these three segmentation problems allows for mutually improved and consistent representation learning. To fuse the predictions of all three heads efficiently, we introduce a parameter-free joint fusion module that dynamically balances the logits and fuses them to create panoptic-part segmentation. Our method is evaluated on the Cityscapes Panoptic Parts (CPP) and Pascal Panoptic Parts (PPP) dataset"},"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":"2212.07671","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T09:04:45Z","cross_cats_sorted":[],"title_canon_sha256":"5abbbf6f6a8d96e086ab7f59de9857166c51d4d0fb6fb73767e69009c5265ad6","abstract_canon_sha256":"d43493746b0ba05b7ccf89ae99e2379efeddb3f522af5c68557de6ef98558e8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:12.678283Z","signature_b64":"VyoAawqgnB1R99stS8w0sU71WrGPrUgmcfsc7F+5Jfj+i6JNuu2JiwKvLiJLwutDpuBfj1OCetOevVnWMYscDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05937314610f9ff3874b88bf92b28c21dea544a6e25d19af57c1236c800a27b4","last_reissued_at":"2026-07-05T05:26:12.677835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:12.677835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task Fusion for Efficient Panoptic-Part Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Ren\\'e Schuster, Sravan Kumar Jagadeesh","submitted_at":"2022-12-15T09:04:45Z","abstract_excerpt":"In this paper, we introduce a novel network that generates semantic, instance, and part segmentation using a shared encoder and effectively fuses them to achieve panoptic-part segmentation. Unifying these three segmentation problems allows for mutually improved and consistent representation learning. To fuse the predictions of all three heads efficiently, we introduce a parameter-free joint fusion module that dynamically balances the logits and fuses them to create panoptic-part segmentation. Our method is evaluated on the Cityscapes Panoptic Parts (CPP) and Pascal Panoptic Parts (PPP) dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07671","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/2212.07671/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":"2212.07671","created_at":"2026-07-05T05:26:12.677894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07671v2","created_at":"2026-07-05T05:26:12.677894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07671","created_at":"2026-07-05T05:26:12.677894+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWJXGFDBB6P7","created_at":"2026-07-05T05:26:12.677894+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWJXGFDBB6P7HB2L","created_at":"2026-07-05T05:26:12.677894+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWJXGFDB","created_at":"2026-07-05T05:26:12.677894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19592","citing_title":"SurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH","json":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH.json","graph_json":"https://pith.science/api/pith-number/AWJXGFDBB6P7HB2LRC7ZFMUMEH/graph.json","events_json":"https://pith.science/api/pith-number/AWJXGFDBB6P7HB2LRC7ZFMUMEH/events.json","paper":"https://pith.science/paper/AWJXGFDB"},"agent_actions":{"view_html":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH","download_json":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH.json","view_paper":"https://pith.science/paper/AWJXGFDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07671&json=true","fetch_graph":"https://pith.science/api/pith-number/AWJXGFDBB6P7HB2LRC7ZFMUMEH/graph.json","fetch_events":"https://pith.science/api/pith-number/AWJXGFDBB6P7HB2LRC7ZFMUMEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH/action/storage_attestation","attest_author":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH/action/author_attestation","sign_citation":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH/action/citation_signature","submit_replication":"https://pith.science/pith/AWJXGFDBB6P7HB2LRC7ZFMUMEH/action/replication_record"}},"created_at":"2026-07-05T05:26:12.677894+00:00","updated_at":"2026-07-05T05:26:12.677894+00:00"}