{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W33BSPHI4OBZ5ZOO273FXNRYTC","short_pith_number":"pith:W33BSPHI","schema_version":"1.0","canonical_sha256":"b6f6193ce8e3839ee5ced7f65bb63898a6585ef2169681007de84c17587068bb","source":{"kind":"arxiv","id":"2207.10392","version":2},"attestation_state":"computed","paper":{"title":"FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic 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, Zhiguo Cao","submitted_at":"2022-07-21T10:06:01Z","abstract_excerpt":"We consider the problem of task-agnostic feature upsampling in dense prediction where an upsampling operator is required to facilitate both region-sensitive tasks like semantic segmentation and detail-sensitive tasks such as image matting. Existing upsampling operators often can work well in either type of the tasks, but not both. In this work, we present FADE, a novel, plug-and-play, and task-agnostic upsampling operator. FADE benefits from three design choices: i) considering encoder and decoder features jointly in upsampling kernel generation; ii) an efficient semi-shift convolutional opera"},"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":"2207.10392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T10:06:01Z","cross_cats_sorted":[],"title_canon_sha256":"8dd1efba2377fa153a2b7d73978f660082abd772edfefe3336e09fbc043b5caf","abstract_canon_sha256":"0ada461d45f0f4f70078bc469c3ea2842a2468b1c415713a7b01a1eca3af2c77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:46.341249Z","signature_b64":"qoNe+q4OaXPMV22f79EUT0as736t8P5rxAkqDUCf/OC2O0PeVPS1+oyBtTH2p8rfTbs3V8gJy9S7J7YAwMJEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6f6193ce8e3839ee5ced7f65bb63898a6585ef2169681007de84c17587068bb","last_reissued_at":"2026-07-05T05:28:46.340853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:46.340853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic 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, Zhiguo Cao","submitted_at":"2022-07-21T10:06:01Z","abstract_excerpt":"We consider the problem of task-agnostic feature upsampling in dense prediction where an upsampling operator is required to facilitate both region-sensitive tasks like semantic segmentation and detail-sensitive tasks such as image matting. Existing upsampling operators often can work well in either type of the tasks, but not both. In this work, we present FADE, a novel, plug-and-play, and task-agnostic upsampling operator. FADE benefits from three design choices: i) considering encoder and decoder features jointly in upsampling kernel generation; ii) an efficient semi-shift convolutional opera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10392","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/2207.10392/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":"2207.10392","created_at":"2026-07-05T05:28:46.340907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10392v2","created_at":"2026-07-05T05:28:46.340907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10392","created_at":"2026-07-05T05:28:46.340907+00:00"},{"alias_kind":"pith_short_12","alias_value":"W33BSPHI4OBZ","created_at":"2026-07-05T05:28:46.340907+00:00"},{"alias_kind":"pith_short_16","alias_value":"W33BSPHI4OBZ5ZOO","created_at":"2026-07-05T05:28:46.340907+00:00"},{"alias_kind":"pith_short_8","alias_value":"W33BSPHI","created_at":"2026-07-05T05:28:46.340907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC","json":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC.json","graph_json":"https://pith.science/api/pith-number/W33BSPHI4OBZ5ZOO273FXNRYTC/graph.json","events_json":"https://pith.science/api/pith-number/W33BSPHI4OBZ5ZOO273FXNRYTC/events.json","paper":"https://pith.science/paper/W33BSPHI"},"agent_actions":{"view_html":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC","download_json":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC.json","view_paper":"https://pith.science/paper/W33BSPHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10392&json=true","fetch_graph":"https://pith.science/api/pith-number/W33BSPHI4OBZ5ZOO273FXNRYTC/graph.json","fetch_events":"https://pith.science/api/pith-number/W33BSPHI4OBZ5ZOO273FXNRYTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC/action/storage_attestation","attest_author":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC/action/author_attestation","sign_citation":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC/action/citation_signature","submit_replication":"https://pith.science/pith/W33BSPHI4OBZ5ZOO273FXNRYTC/action/replication_record"}},"created_at":"2026-07-05T05:28:46.340907+00:00","updated_at":"2026-07-05T05:28:46.340907+00:00"}