{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SV7CF53QZDRKYHLJHD4JCEVDJZ","short_pith_number":"pith:SV7CF53Q","schema_version":"1.0","canonical_sha256":"957e22f770c8e2ac1d6938f89112a34e6435534f6a60bf37124511aa00e01c72","source":{"kind":"arxiv","id":"2107.06278","version":2},"attestation_state":"computed","paper":{"title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Alexander Kirillov, Bowen Cheng","submitted_at":"2021-07-13T17:59:50Z","abstract_excerpt":"Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. Overall, the proposed mask class"},"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":"2107.06278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-13T17:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"ee3a28cc911d0526e4d24aa060e014b778c08fffe9252bd119cce48a0db0e375","abstract_canon_sha256":"cb74381eceb09beead48c3e4f882e0403ca3c677d95243bfd5b18c13861b1ca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:33.843692Z","signature_b64":"D/RyBZNTDevag7k3iP7wVEoEBzNMTsfQzKLNnhaTK3F9fSP1ylbaIT9yKUjhSoJvq4n5WobIen9apMxRBg+eBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"957e22f770c8e2ac1d6938f89112a34e6435534f6a60bf37124511aa00e01c72","last_reissued_at":"2026-07-05T03:27:33.843166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:33.843166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Alexander Kirillov, Bowen Cheng","submitted_at":"2021-07-13T17:59:50Z","abstract_excerpt":"Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks in a unified manner using the exact same model, loss, and training procedure. Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction. Overall, the proposed mask class"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06278","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/2107.06278/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":"2107.06278","created_at":"2026-07-05T03:27:33.843225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.06278v2","created_at":"2026-07-05T03:27:33.843225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06278","created_at":"2026-07-05T03:27:33.843225+00:00"},{"alias_kind":"pith_short_12","alias_value":"SV7CF53QZDRK","created_at":"2026-07-05T03:27:33.843225+00:00"},{"alias_kind":"pith_short_16","alias_value":"SV7CF53QZDRKYHLJ","created_at":"2026-07-05T03:27:33.843225+00:00"},{"alias_kind":"pith_short_8","alias_value":"SV7CF53Q","created_at":"2026-07-05T03:27:33.843225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20561","citing_title":"TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25072","citing_title":"Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ","json":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ.json","graph_json":"https://pith.science/api/pith-number/SV7CF53QZDRKYHLJHD4JCEVDJZ/graph.json","events_json":"https://pith.science/api/pith-number/SV7CF53QZDRKYHLJHD4JCEVDJZ/events.json","paper":"https://pith.science/paper/SV7CF53Q"},"agent_actions":{"view_html":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ","download_json":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ.json","view_paper":"https://pith.science/paper/SV7CF53Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.06278&json=true","fetch_graph":"https://pith.science/api/pith-number/SV7CF53QZDRKYHLJHD4JCEVDJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SV7CF53QZDRKYHLJHD4JCEVDJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ/action/storage_attestation","attest_author":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ/action/author_attestation","sign_citation":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ/action/citation_signature","submit_replication":"https://pith.science/pith/SV7CF53QZDRKYHLJHD4JCEVDJZ/action/replication_record"}},"created_at":"2026-07-05T03:27:33.843225+00:00","updated_at":"2026-07-05T03:27:33.843225+00:00"}