{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UEI36MM5KUDII7TUFONS74NKR4","short_pith_number":"pith:UEI36MM5","schema_version":"1.0","canonical_sha256":"a111bf319d5506847e742b9b2ff1aa8f38914021b1345299aa2cd32c3d4fba8f","source":{"kind":"arxiv","id":"1906.05404","version":1},"attestation_state":"computed","paper":{"title":"Topology-Preserving Deep Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG"],"primary_cat":"cs.CV","authors_text":"Chao Chen, Dimitris Samaras, Li Fuxin, Xiaoling Hu","submitted_at":"2019-06-12T22:12:44Z","abstract_excerpt":"Segmentation algorithms are prone to make topological errors on fine-scale structures, e.g., broken connections. We propose a novel method that learns to segment with correct topology. In particular, we design a continuous-valued loss function that enforces a segmentation to have the same topology as the ground truth, i.e., having the same Betti number. The proposed topology-preserving loss function is differentiable and we incorporate it into end-to-end training of a deep neural network. Our method achieves much better performance on the Betti number error, which directly accounts for the top"},"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":"1906.05404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-12T22:12:44Z","cross_cats_sorted":["cs.CG"],"title_canon_sha256":"0b8a32adefe8e2c2e57d9219aba0c1485c9674e4d19a4f19607159961869d447","abstract_canon_sha256":"076b85baa8f270acb0dfa14ff7188204f355e65321880bb3df455e6c6f07e44f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:14.023071Z","signature_b64":"Vf+9RZJZFJQG1ltcZO/rJz6m8PUCK8I/UbrKgJw4p6mlUeIddQ91emWyJbQzzdRcqKeL8Y6XaclAEnTEp4lRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a111bf319d5506847e742b9b2ff1aa8f38914021b1345299aa2cd32c3d4fba8f","last_reissued_at":"2026-05-17T23:43:14.022630Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:14.022630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topology-Preserving Deep Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG"],"primary_cat":"cs.CV","authors_text":"Chao Chen, Dimitris Samaras, Li Fuxin, Xiaoling Hu","submitted_at":"2019-06-12T22:12:44Z","abstract_excerpt":"Segmentation algorithms are prone to make topological errors on fine-scale structures, e.g., broken connections. We propose a novel method that learns to segment with correct topology. In particular, we design a continuous-valued loss function that enforces a segmentation to have the same topology as the ground truth, i.e., having the same Betti number. The proposed topology-preserving loss function is differentiable and we incorporate it into end-to-end training of a deep neural network. Our method achieves much better performance on the Betti number error, which directly accounts for the top"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05404","kind":"arxiv","version":1},"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":"1906.05404","created_at":"2026-05-17T23:43:14.022700+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05404v1","created_at":"2026-05-17T23:43:14.022700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05404","created_at":"2026-05-17T23:43:14.022700+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEI36MM5KUDI","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEI36MM5KUDII7TU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEI36MM5","created_at":"2026-05-18T12:33:30.264802+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/UEI36MM5KUDII7TUFONS74NKR4","json":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4.json","graph_json":"https://pith.science/api/pith-number/UEI36MM5KUDII7TUFONS74NKR4/graph.json","events_json":"https://pith.science/api/pith-number/UEI36MM5KUDII7TUFONS74NKR4/events.json","paper":"https://pith.science/paper/UEI36MM5"},"agent_actions":{"view_html":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4","download_json":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4.json","view_paper":"https://pith.science/paper/UEI36MM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05404&json=true","fetch_graph":"https://pith.science/api/pith-number/UEI36MM5KUDII7TUFONS74NKR4/graph.json","fetch_events":"https://pith.science/api/pith-number/UEI36MM5KUDII7TUFONS74NKR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4/action/storage_attestation","attest_author":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4/action/author_attestation","sign_citation":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4/action/citation_signature","submit_replication":"https://pith.science/pith/UEI36MM5KUDII7TUFONS74NKR4/action/replication_record"}},"created_at":"2026-05-17T23:43:14.022700+00:00","updated_at":"2026-05-17T23:43:14.022700+00:00"}