{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MO66DRQYV5S4OWAPDNGWZEFY3K","short_pith_number":"pith:MO66DRQY","schema_version":"1.0","canonical_sha256":"63bde1c618af65c7580f1b4d6c90b8da815b6fdf70602377251a673e5af5215a","source":{"kind":"arxiv","id":"1911.05250","version":2},"attestation_state":"computed","paper":{"title":"Location-aware Upsampling for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anda Cheng, Jian Cheng, Peisong Wang, Qiang Chen, Xiangyu He, Zitao Mo","submitted_at":"2019-11-13T02:15:06Z","abstract_excerpt":"Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics, this paper aims to introduce location supervision into semantic segmentation. Based on this idea, we present a Location-aware Upsampling (LaU) that adaptively refines the interpolating coordinates with trainable offsets. Then, location-aware losses are established by encouraging pixels to move towards well-classified locations. An LaU is offset prediction coupled with interpolation, which is trained end-to-end to gen"},"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":"1911.05250","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-11-13T02:15:06Z","cross_cats_sorted":[],"title_canon_sha256":"43d8262fa0b0a65105e434e813067c9abc7bfbaa01391c87aa913438798a36c1","abstract_canon_sha256":"0ec52bc2cffd9daa325b69b4292a424d04e5fea45126c8b117e6c665d1c37a7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:11.738891Z","signature_b64":"xqPHwA8bNn3EOyXIO8UrB93zKIqoSg5fhic1/bp2NEtx73udbOC30BMVAcJRnysqARvQdTuFMfzWWW5S4q7XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63bde1c618af65c7580f1b4d6c90b8da815b6fdf70602377251a673e5af5215a","last_reissued_at":"2026-07-05T00:19:11.738428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:11.738428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Location-aware Upsampling for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anda Cheng, Jian Cheng, Peisong Wang, Qiang Chen, Xiangyu He, Zitao Mo","submitted_at":"2019-11-13T02:15:06Z","abstract_excerpt":"Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics, this paper aims to introduce location supervision into semantic segmentation. Based on this idea, we present a Location-aware Upsampling (LaU) that adaptively refines the interpolating coordinates with trainable offsets. Then, location-aware losses are established by encouraging pixels to move towards well-classified locations. An LaU is offset prediction coupled with interpolation, which is trained end-to-end to gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05250","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/1911.05250/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":"1911.05250","created_at":"2026-07-05T00:19:11.738482+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05250v2","created_at":"2026-07-05T00:19:11.738482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05250","created_at":"2026-07-05T00:19:11.738482+00:00"},{"alias_kind":"pith_short_12","alias_value":"MO66DRQYV5S4","created_at":"2026-07-05T00:19:11.738482+00:00"},{"alias_kind":"pith_short_16","alias_value":"MO66DRQYV5S4OWAP","created_at":"2026-07-05T00:19:11.738482+00:00"},{"alias_kind":"pith_short_8","alias_value":"MO66DRQY","created_at":"2026-07-05T00:19:11.738482+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/MO66DRQYV5S4OWAPDNGWZEFY3K","json":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K.json","graph_json":"https://pith.science/api/pith-number/MO66DRQYV5S4OWAPDNGWZEFY3K/graph.json","events_json":"https://pith.science/api/pith-number/MO66DRQYV5S4OWAPDNGWZEFY3K/events.json","paper":"https://pith.science/paper/MO66DRQY"},"agent_actions":{"view_html":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K","download_json":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K.json","view_paper":"https://pith.science/paper/MO66DRQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05250&json=true","fetch_graph":"https://pith.science/api/pith-number/MO66DRQYV5S4OWAPDNGWZEFY3K/graph.json","fetch_events":"https://pith.science/api/pith-number/MO66DRQYV5S4OWAPDNGWZEFY3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K/action/storage_attestation","attest_author":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K/action/author_attestation","sign_citation":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K/action/citation_signature","submit_replication":"https://pith.science/pith/MO66DRQYV5S4OWAPDNGWZEFY3K/action/replication_record"}},"created_at":"2026-07-05T00:19:11.738482+00:00","updated_at":"2026-07-05T00:19:11.738482+00:00"}