{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XHB7SDV6TPPPV3OCHGOPB5I6UE","short_pith_number":"pith:XHB7SDV6","schema_version":"1.0","canonical_sha256":"b9c3f90ebe9bdefaedc2399cf0f51ea11feaaa1bd9b1b0d38020b34b0b6c87c0","source":{"kind":"arxiv","id":"2203.15102","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Semantic Segmentation: A Prototype View","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ender Konukoglu, Luc Van Gool, Tianfei Zhou, Wenguan Wang","submitted_at":"2022-03-28T21:15:32Z","abstract_excerpt":"Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, this study uncovers several limitations of such parametric segmentation regime, and proposes a nonparametric alternative based on non-learnable prototypes. Instead of prior methods learning a single weight/query vector for each class in a fully parametric manne"},"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":"2203.15102","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-28T21:15:32Z","cross_cats_sorted":[],"title_canon_sha256":"81a7bacd2b17142457d0b39a7b26dfaeae0fec177d3deee53ac604d897c4ef05","abstract_canon_sha256":"b8294dbc1135b9b4993f6e175a7cf73aba54437c5983ad66a29d67dcafd04378"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:13.055037Z","signature_b64":"l2NORf8THPwio+Z4mh5fFX0KvkUhNhwyqP6vK3e6cAJIFw6cS0ubRYDdIga+vVHiTwm5o4xF1jViJVNywG7SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c3f90ebe9bdefaedc2399cf0f51ea11feaaa1bd9b1b0d38020b34b0b6c87c0","last_reissued_at":"2026-07-05T04:11:13.054620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:13.054620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Semantic Segmentation: A Prototype View","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ender Konukoglu, Luc Van Gool, Tianfei Zhou, Wenguan Wang","submitted_at":"2022-03-28T21:15:32Z","abstract_excerpt":"Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, this study uncovers several limitations of such parametric segmentation regime, and proposes a nonparametric alternative based on non-learnable prototypes. Instead of prior methods learning a single weight/query vector for each class in a fully parametric manne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15102","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/2203.15102/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":"2203.15102","created_at":"2026-07-05T04:11:13.054678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15102v2","created_at":"2026-07-05T04:11:13.054678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15102","created_at":"2026-07-05T04:11:13.054678+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHB7SDV6TPPP","created_at":"2026-07-05T04:11:13.054678+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHB7SDV6TPPPV3OC","created_at":"2026-07-05T04:11:13.054678+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHB7SDV6","created_at":"2026-07-05T04:11:13.054678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07416","citing_title":"VCDP: Variation-Conditioned Distributional Proxy Learning for Semi-Supervised Medical Image Segmentation","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE","json":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE.json","graph_json":"https://pith.science/api/pith-number/XHB7SDV6TPPPV3OCHGOPB5I6UE/graph.json","events_json":"https://pith.science/api/pith-number/XHB7SDV6TPPPV3OCHGOPB5I6UE/events.json","paper":"https://pith.science/paper/XHB7SDV6"},"agent_actions":{"view_html":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE","download_json":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE.json","view_paper":"https://pith.science/paper/XHB7SDV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15102&json=true","fetch_graph":"https://pith.science/api/pith-number/XHB7SDV6TPPPV3OCHGOPB5I6UE/graph.json","fetch_events":"https://pith.science/api/pith-number/XHB7SDV6TPPPV3OCHGOPB5I6UE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE/action/storage_attestation","attest_author":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE/action/author_attestation","sign_citation":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE/action/citation_signature","submit_replication":"https://pith.science/pith/XHB7SDV6TPPPV3OCHGOPB5I6UE/action/replication_record"}},"created_at":"2026-07-05T04:11:13.054678+00:00","updated_at":"2026-07-05T04:11:13.054678+00:00"}