{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SZSHKE2Z4UZ3WO2D3QEFVDE3WD","short_pith_number":"pith:SZSHKE2Z","schema_version":"1.0","canonical_sha256":"9664751359e533bb3b43dc085a8c9bb0c39887141c4a9d8e75750b3db18f5033","source":{"kind":"arxiv","id":"1802.08290","version":2},"attestation_state":"computed","paper":{"title":"Locally Adaptive Learning Loss for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aiguo Gu, Jian Xu, Jinjiang Guo, Pengyuan Ren, Weixin Wu","submitted_at":"2018-02-23T05:18:35Z","abstract_excerpt":"We propose a novel locally adaptive learning estimator for enhancing the inter- and intra- discriminative capabilities of Deep Neural Networks, which can be used as improved loss layer for semantic image segmentation tasks. Most loss layers compute pixel-wise cost between feature maps and ground truths, ignoring spatial layouts and interactions between neighboring pixels with same object category, and thus networks cannot be effectively sensitive to intra-class connections. Stride by stride, our method firstly conducts adaptive pooling filter operating over predicted feature maps, aiming to me"},"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":"1802.08290","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-23T05:18:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"172d9035ade133f0d30ddc627d71d4525e5f978f93b718f77e2125e1bc1f5db3","abstract_canon_sha256":"4a45b745c112f28cb5ff6bcd310ed4b1cb9413c508c2bf296de7a2cb4d5377f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:30.954596Z","signature_b64":"yu3FEsXdB1lQzv45kyeeXKYMtSgj5Aq64SL9VH7m2zUX8wHF0t9OrwunNLHp/LEoNBYlVOuYmwwFD7LO12nhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9664751359e533bb3b43dc085a8c9bb0c39887141c4a9d8e75750b3db18f5033","last_reissued_at":"2026-05-18T00:18:30.954243Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:30.954243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locally Adaptive Learning Loss for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aiguo Gu, Jian Xu, Jinjiang Guo, Pengyuan Ren, Weixin Wu","submitted_at":"2018-02-23T05:18:35Z","abstract_excerpt":"We propose a novel locally adaptive learning estimator for enhancing the inter- and intra- discriminative capabilities of Deep Neural Networks, which can be used as improved loss layer for semantic image segmentation tasks. Most loss layers compute pixel-wise cost between feature maps and ground truths, ignoring spatial layouts and interactions between neighboring pixels with same object category, and thus networks cannot be effectively sensitive to intra-class connections. Stride by stride, our method firstly conducts adaptive pooling filter operating over predicted feature maps, aiming to me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08290","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":""},"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":"1802.08290","created_at":"2026-05-18T00:18:30.954300+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08290v2","created_at":"2026-05-18T00:18:30.954300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08290","created_at":"2026-05-18T00:18:30.954300+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZSHKE2Z4UZ3","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZSHKE2Z4UZ3WO2D","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZSHKE2Z","created_at":"2026-05-18T12:32:53.628368+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/SZSHKE2Z4UZ3WO2D3QEFVDE3WD","json":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD.json","graph_json":"https://pith.science/api/pith-number/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/graph.json","events_json":"https://pith.science/api/pith-number/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/events.json","paper":"https://pith.science/paper/SZSHKE2Z"},"agent_actions":{"view_html":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD","download_json":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD.json","view_paper":"https://pith.science/paper/SZSHKE2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08290&json=true","fetch_graph":"https://pith.science/api/pith-number/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/graph.json","fetch_events":"https://pith.science/api/pith-number/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/action/storage_attestation","attest_author":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/action/author_attestation","sign_citation":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/action/citation_signature","submit_replication":"https://pith.science/pith/SZSHKE2Z4UZ3WO2D3QEFVDE3WD/action/replication_record"}},"created_at":"2026-05-18T00:18:30.954300+00:00","updated_at":"2026-05-18T00:18:30.954300+00:00"}