{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DNX6NUY6H3J5ORZES57VEU6PJB","short_pith_number":"pith:DNX6NUY6","schema_version":"1.0","canonical_sha256":"1b6fe6d31e3ed3d74724977f5253cf485a2e7cb61a3bf127f012ec23deeef3a1","source":{"kind":"arxiv","id":"1611.06612","version":3},"attestation_state":"computed","paper":{"title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton Milan, Chunhua Shen, Guosheng Lin, Ian Reid","submitted_at":"2016-11-20T23:39:52Z","abstract_excerpt":"Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections."},"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":"1611.06612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-20T23:39:52Z","cross_cats_sorted":[],"title_canon_sha256":"390f655613589ad091c917efa7b879e8a2704876a34944d100dcbac2cc6a62da","abstract_canon_sha256":"3df6dd2fa9561e05ccdce17c6821b57d9b15ea566b30499b2fc6bb2bcab38c6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:44.992646Z","signature_b64":"hlmyFAx7Mh2Vd0RXyE6OAAF742IUB6PNn1XghkKjRMkNyAr/Bse3PS4dadCr1jDeu8/95i1CBeu4DVuLaIeHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b6fe6d31e3ed3d74724977f5253cf485a2e7cb61a3bf127f012ec23deeef3a1","last_reissued_at":"2026-05-18T00:56:44.992021Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:44.992021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton Milan, Chunhua Shen, Guosheng Lin, Ian Reid","submitted_at":"2016-11-20T23:39:52Z","abstract_excerpt":"Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06612","kind":"arxiv","version":3},"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":"1611.06612","created_at":"2026-05-18T00:56:44.992127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06612v3","created_at":"2026-05-18T00:56:44.992127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06612","created_at":"2026-05-18T00:56:44.992127+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNX6NUY6H3J5","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNX6NUY6H3J5ORZE","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNX6NUY6","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.03089","citing_title":"SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB","json":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB.json","graph_json":"https://pith.science/api/pith-number/DNX6NUY6H3J5ORZES57VEU6PJB/graph.json","events_json":"https://pith.science/api/pith-number/DNX6NUY6H3J5ORZES57VEU6PJB/events.json","paper":"https://pith.science/paper/DNX6NUY6"},"agent_actions":{"view_html":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB","download_json":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB.json","view_paper":"https://pith.science/paper/DNX6NUY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06612&json=true","fetch_graph":"https://pith.science/api/pith-number/DNX6NUY6H3J5ORZES57VEU6PJB/graph.json","fetch_events":"https://pith.science/api/pith-number/DNX6NUY6H3J5ORZES57VEU6PJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB/action/storage_attestation","attest_author":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB/action/author_attestation","sign_citation":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB/action/citation_signature","submit_replication":"https://pith.science/pith/DNX6NUY6H3J5ORZES57VEU6PJB/action/replication_record"}},"created_at":"2026-05-18T00:56:44.992127+00:00","updated_at":"2026-05-18T00:56:44.992127+00:00"}