{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P2Z4PM2S6H42G3K3ZNHTFEUMFC","short_pith_number":"pith:P2Z4PM2S","schema_version":"1.0","canonical_sha256":"7eb3c7b352f1f9a36d5bcb4f32928c28a774edf889187b0712789df7247f9abf","source":{"kind":"arxiv","id":"2209.12866","version":2},"attestation_state":"computed","paper":{"title":"SAPA: Similarity-Aware Point Affiliation for Feature Upsampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Lu, Hongtao Fu, Wenze Liu, Yuliang Liu, Zhiguo Cao, Zixuan Ye","submitted_at":"2022-09-26T17:32:25Z","abstract_excerpt":"We introduce point affiliation into feature upsampling, a notion that describes the affiliation of each upsampled point to a semantic cluster formed by local decoder feature points with semantic similarity. By rethinking point affiliation, we present a generic formulation for generating upsampling kernels. The kernels encourage not only semantic smoothness but also boundary sharpness in the upsampled feature maps. Such properties are particularly useful for some dense prediction tasks such as semantic segmentation. The key idea of our formulation is to generate similarity-aware kernels by comp"},"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":"2209.12866","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-26T17:32:25Z","cross_cats_sorted":[],"title_canon_sha256":"ab94c0903212e2cd17f2552367661d6d64ef47d9820430a608336c4fb7a143d9","abstract_canon_sha256":"ee7d3e6680d1842a62af9cb2a4158fb1ca5c3b9a4c63de2f491d01bc389f4515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:47.334621Z","signature_b64":"4nUJkdOj7ZGEmefhY/uHEQskjtfq77j1IdL+6tObwDrWf/drvF+G7CrDQ2Rgx+X8gn8CUm3Vu1C2L02s0BuKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eb3c7b352f1f9a36d5bcb4f32928c28a774edf889187b0712789df7247f9abf","last_reissued_at":"2026-07-05T05:28:47.334093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:47.334093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAPA: Similarity-Aware Point Affiliation for Feature Upsampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Lu, Hongtao Fu, Wenze Liu, Yuliang Liu, Zhiguo Cao, Zixuan Ye","submitted_at":"2022-09-26T17:32:25Z","abstract_excerpt":"We introduce point affiliation into feature upsampling, a notion that describes the affiliation of each upsampled point to a semantic cluster formed by local decoder feature points with semantic similarity. By rethinking point affiliation, we present a generic formulation for generating upsampling kernels. The kernels encourage not only semantic smoothness but also boundary sharpness in the upsampled feature maps. Such properties are particularly useful for some dense prediction tasks such as semantic segmentation. The key idea of our formulation is to generate similarity-aware kernels by comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12866","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/2209.12866/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":"2209.12866","created_at":"2026-07-05T05:28:47.334149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12866v2","created_at":"2026-07-05T05:28:47.334149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12866","created_at":"2026-07-05T05:28:47.334149+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2Z4PM2S6H42","created_at":"2026-07-05T05:28:47.334149+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2Z4PM2S6H42G3K3","created_at":"2026-07-05T05:28:47.334149+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2Z4PM2S","created_at":"2026-07-05T05:28:47.334149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17472","citing_title":"Weighted Reverse Convolution for Feature Upsampling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17472","citing_title":"Weighted Reverse Convolution for Feature Upsampling","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC","json":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC.json","graph_json":"https://pith.science/api/pith-number/P2Z4PM2S6H42G3K3ZNHTFEUMFC/graph.json","events_json":"https://pith.science/api/pith-number/P2Z4PM2S6H42G3K3ZNHTFEUMFC/events.json","paper":"https://pith.science/paper/P2Z4PM2S"},"agent_actions":{"view_html":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC","download_json":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC.json","view_paper":"https://pith.science/paper/P2Z4PM2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12866&json=true","fetch_graph":"https://pith.science/api/pith-number/P2Z4PM2S6H42G3K3ZNHTFEUMFC/graph.json","fetch_events":"https://pith.science/api/pith-number/P2Z4PM2S6H42G3K3ZNHTFEUMFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC/action/storage_attestation","attest_author":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC/action/author_attestation","sign_citation":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC/action/citation_signature","submit_replication":"https://pith.science/pith/P2Z4PM2S6H42G3K3ZNHTFEUMFC/action/replication_record"}},"created_at":"2026-07-05T05:28:47.334149+00:00","updated_at":"2026-07-05T05:28:47.334149+00:00"}