{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:G4AGEJK2BUQ3H3PJAKFVKJERPN","short_pith_number":"pith:G4AGEJK2","schema_version":"1.0","canonical_sha256":"370062255a0d21b3ede9028b5524917b69e90319e4e2fcfbd80e3ef3a0916e2a","source":{"kind":"arxiv","id":"1801.01317","version":1},"attestation_state":"computed","paper":{"title":"Semantic Segmentation via Highly Fused Convolutional Network with Multiple Soft Cost Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junqiao Zhao, Linting Guan, Tao Yang, Yan Wu","submitted_at":"2018-01-04T11:55:55Z","abstract_excerpt":"Semantic image segmentation is one of the most challenged tasks in computer vision. In this paper, we propose a highly fused convolutional network, which consists of three parts: feature downsampling, combined feature upsampling and multiple predictions. We adopt a strategy of multiple steps of upsampling and combined feature maps in pooling layers with its corresponding unpooling layers. Then we bring out multiple pre-outputs, each pre-output is generated from an unpooling layer by one-step upsampling. Finally, we concatenate these pre-outputs to get the final output. As a result, our propose"},"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":"1801.01317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-04T11:55:55Z","cross_cats_sorted":[],"title_canon_sha256":"ee9bf11c4d8427850a0f7593706b181bb433dc51f9aee355ddc92168c061aa17","abstract_canon_sha256":"89c1e01f529c068a144ff7e036b9d8fe22fbbf730bd227bd9026737ec2fef50a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:42.466849Z","signature_b64":"rBD2dH1rAbgUoFlx8N2Q3EkmY3LI7y0iINvk9tE9ZCmxp++YvZBg0XQIT4yOwXu9eemGM4/HajwAppqK7r0yAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"370062255a0d21b3ede9028b5524917b69e90319e4e2fcfbd80e3ef3a0916e2a","last_reissued_at":"2026-05-18T00:26:42.466250Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:42.466250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Segmentation via Highly Fused Convolutional Network with Multiple Soft Cost Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junqiao Zhao, Linting Guan, Tao Yang, Yan Wu","submitted_at":"2018-01-04T11:55:55Z","abstract_excerpt":"Semantic image segmentation is one of the most challenged tasks in computer vision. In this paper, we propose a highly fused convolutional network, which consists of three parts: feature downsampling, combined feature upsampling and multiple predictions. We adopt a strategy of multiple steps of upsampling and combined feature maps in pooling layers with its corresponding unpooling layers. Then we bring out multiple pre-outputs, each pre-output is generated from an unpooling layer by one-step upsampling. Finally, we concatenate these pre-outputs to get the final output. As a result, our propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01317","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":"1801.01317","created_at":"2026-05-18T00:26:42.466351+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.01317v1","created_at":"2026-05-18T00:26:42.466351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01317","created_at":"2026-05-18T00:26:42.466351+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4AGEJK2BUQ3","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4AGEJK2BUQ3H3PJ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4AGEJK2","created_at":"2026-05-18T12:32:25.280505+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/G4AGEJK2BUQ3H3PJAKFVKJERPN","json":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN.json","graph_json":"https://pith.science/api/pith-number/G4AGEJK2BUQ3H3PJAKFVKJERPN/graph.json","events_json":"https://pith.science/api/pith-number/G4AGEJK2BUQ3H3PJAKFVKJERPN/events.json","paper":"https://pith.science/paper/G4AGEJK2"},"agent_actions":{"view_html":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN","download_json":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN.json","view_paper":"https://pith.science/paper/G4AGEJK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.01317&json=true","fetch_graph":"https://pith.science/api/pith-number/G4AGEJK2BUQ3H3PJAKFVKJERPN/graph.json","fetch_events":"https://pith.science/api/pith-number/G4AGEJK2BUQ3H3PJAKFVKJERPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN/action/storage_attestation","attest_author":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN/action/author_attestation","sign_citation":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN/action/citation_signature","submit_replication":"https://pith.science/pith/G4AGEJK2BUQ3H3PJAKFVKJERPN/action/replication_record"}},"created_at":"2026-05-18T00:26:42.466351+00:00","updated_at":"2026-05-18T00:26:42.466351+00:00"}