{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RXM5TAWB2U4U6VFPB6JJ2I35IL","short_pith_number":"pith:RXM5TAWB","schema_version":"1.0","canonical_sha256":"8dd9d982c1d5394f54af0f929d237d42c94dc4300e3074efdd8498bd2c5f5876","source":{"kind":"arxiv","id":"1904.02216","version":1},"attestation_state":"computed","paper":{"title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanchao Li, Haoqiang Fan, Jian Sun, Pengfei Xiong","submitted_at":"2019-04-03T19:45:17Z","abstract_excerpt":"This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints. Our proposed network starts from a single lightweight backbone and aggregates discriminative features through sub-network and sub-stage cascade respectively. Based on the multi-scale feature propagation, DFANet substantially reduces the number of parameters, but still obtains sufficient receptive field and enhances the model learning ability, which strikes a balance between the speed and segmentation performance. Experiments on Cityscapes and CamVid datasets demonstr"},"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":"1904.02216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-03T19:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"e702c07332d9992f02c5a0674a7aca928d1e30a0b80847b4c784b6ac938caaf5","abstract_canon_sha256":"99837de0d16d6f7a99504d69e4b1826fd7100eda16376888db17b8f6a52def49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:24.206313Z","signature_b64":"cpX3y2Bo5Wg6BrRDiTOy6mXJwtg7hBh8eUhJod9yt1em+MrAaO+DydV3rC65pJevv91KPvGo8uY90dorPrRBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dd9d982c1d5394f54af0f929d237d42c94dc4300e3074efdd8498bd2c5f5876","last_reissued_at":"2026-05-17T23:49:24.205862Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:24.205862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanchao Li, Haoqiang Fan, Jian Sun, Pengfei Xiong","submitted_at":"2019-04-03T19:45:17Z","abstract_excerpt":"This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints. Our proposed network starts from a single lightweight backbone and aggregates discriminative features through sub-network and sub-stage cascade respectively. Based on the multi-scale feature propagation, DFANet substantially reduces the number of parameters, but still obtains sufficient receptive field and enhances the model learning ability, which strikes a balance between the speed and segmentation performance. Experiments on Cityscapes and CamVid datasets demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02216","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":"1904.02216","created_at":"2026-05-17T23:49:24.205938+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02216v1","created_at":"2026-05-17T23:49:24.205938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02216","created_at":"2026-05-17T23:49:24.205938+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXM5TAWB2U4U","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXM5TAWB2U4U6VFP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXM5TAWB","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11428","citing_title":"ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL","json":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL.json","graph_json":"https://pith.science/api/pith-number/RXM5TAWB2U4U6VFPB6JJ2I35IL/graph.json","events_json":"https://pith.science/api/pith-number/RXM5TAWB2U4U6VFPB6JJ2I35IL/events.json","paper":"https://pith.science/paper/RXM5TAWB"},"agent_actions":{"view_html":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL","download_json":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL.json","view_paper":"https://pith.science/paper/RXM5TAWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02216&json=true","fetch_graph":"https://pith.science/api/pith-number/RXM5TAWB2U4U6VFPB6JJ2I35IL/graph.json","fetch_events":"https://pith.science/api/pith-number/RXM5TAWB2U4U6VFPB6JJ2I35IL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL/action/storage_attestation","attest_author":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL/action/author_attestation","sign_citation":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL/action/citation_signature","submit_replication":"https://pith.science/pith/RXM5TAWB2U4U6VFPB6JJ2I35IL/action/replication_record"}},"created_at":"2026-05-17T23:49:24.205938+00:00","updated_at":"2026-05-17T23:49:24.205938+00:00"}