{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3VZFU4ANQQS7EBPHCATJF6TV2B","short_pith_number":"pith:3VZFU4AN","schema_version":"1.0","canonical_sha256":"dd725a700d8425f205e7102692fa75d05c16b4cd6125f7111fb238c5988198b3","source":{"kind":"arxiv","id":"1805.04628","version":2},"attestation_state":"computed","paper":{"title":"Constrained-CNN losses for weakly supervised segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Granger, Hoel Kervadec, Ismail Ben Ayed, Jose Dolz, Meng Tang, Yuri Boykov","submitted_at":"2018-05-12T00:51:54Z","abstract_excerpt":"Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. Enforcing high-order (global) inequality constraints on the network output (for instance, to constrain the size of the target region) can leverage unlabeled data, guiding the training process with domain-specific knowledge. Inequality constraints are very flexible because they do not assume exact prior knowledge. However, constrained Lagrangian dual optimization has been "},"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":"1805.04628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-12T00:51:54Z","cross_cats_sorted":[],"title_canon_sha256":"480c60422b220b8f0fcc09625f88277c44a58a27a1978d54811484bbfe4df9a2","abstract_canon_sha256":"a4804408043d80fac1a22341f6de2297fbec4dc3a39fa8519186247e62cc2aa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:54.570647Z","signature_b64":"muFWVdlWSVWDVulrzwmwkweeVd/d8B+QbO8ql3pNgGfLZdgJcbJf5e19YwfpkXNGABobHtjso5anReaCk0FaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd725a700d8425f205e7102692fa75d05c16b4cd6125f7111fb238c5988198b3","last_reissued_at":"2026-05-17T23:51:54.570159Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:54.570159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained-CNN losses for weakly supervised segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Granger, Hoel Kervadec, Ismail Ben Ayed, Jose Dolz, Meng Tang, Yuri Boykov","submitted_at":"2018-05-12T00:51:54Z","abstract_excerpt":"Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. Enforcing high-order (global) inequality constraints on the network output (for instance, to constrain the size of the target region) can leverage unlabeled data, guiding the training process with domain-specific knowledge. Inequality constraints are very flexible because they do not assume exact prior knowledge. However, constrained Lagrangian dual optimization has been "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04628","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":"1805.04628","created_at":"2026-05-17T23:51:54.570246+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.04628v2","created_at":"2026-05-17T23:51:54.570246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04628","created_at":"2026-05-17T23:51:54.570246+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VZFU4ANQQS7","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VZFU4ANQQS7EBPH","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VZFU4AN","created_at":"2026-05-18T12:32:05.422762+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/3VZFU4ANQQS7EBPHCATJF6TV2B","json":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B.json","graph_json":"https://pith.science/api/pith-number/3VZFU4ANQQS7EBPHCATJF6TV2B/graph.json","events_json":"https://pith.science/api/pith-number/3VZFU4ANQQS7EBPHCATJF6TV2B/events.json","paper":"https://pith.science/paper/3VZFU4AN"},"agent_actions":{"view_html":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B","download_json":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B.json","view_paper":"https://pith.science/paper/3VZFU4AN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.04628&json=true","fetch_graph":"https://pith.science/api/pith-number/3VZFU4ANQQS7EBPHCATJF6TV2B/graph.json","fetch_events":"https://pith.science/api/pith-number/3VZFU4ANQQS7EBPHCATJF6TV2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/action/storage_attestation","attest_author":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/action/author_attestation","sign_citation":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/action/citation_signature","submit_replication":"https://pith.science/pith/3VZFU4ANQQS7EBPHCATJF6TV2B/action/replication_record"}},"created_at":"2026-05-17T23:51:54.570246+00:00","updated_at":"2026-05-17T23:51:54.570246+00:00"}