{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JPES3ZR66YLLD3TPS7SDHWS3VU","short_pith_number":"pith:JPES3ZR6","schema_version":"1.0","canonical_sha256":"4bc92de63ef616b1ee6f97e433da5bad083bcd2638c9b0a4a21982f4db832d50","source":{"kind":"arxiv","id":"2012.01733","version":2},"attestation_state":"computed","paper":{"title":"Dual Refinement Feature Pyramid Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Jialiang Ma","submitted_at":"2020-12-03T07:17:03Z","abstract_excerpt":"FPN is a common component used in object detectors, it supplements multi-scale information by adjacent level features interpolation and summation. However, due to the existence of nonlinear operations and the convolutional layers with different output dimensions, the relationship between different levels is much more complex, the pixel-wise summation is not an efficient approach. In this paper, we first analyze the design defects from pixel level and feature map level. Then, we design a novel parameter-free feature pyramid networks named Dual Refinement Feature Pyramid Networks (DRFPN) for the"},"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":"2012.01733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-03T07:17:03Z","cross_cats_sorted":[],"title_canon_sha256":"c441871a106a0cf40d9f7c4c0fcd29ff6c0969e2af511df2efb8e16d900bbbc1","abstract_canon_sha256":"7c07b30ac11c0b83b12c52a6713b3f7f8217871eae4a205158cb3ea1e0a4f5a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:56.970012Z","signature_b64":"nyJwhFNthvfJUaKpF0nnoEIX3eu+B3DVzw6W5+Vy/CpxL2OcfjPuImgzndP0njrSTjn12b1MD9qOk+BHJP2PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc92de63ef616b1ee6f97e433da5bad083bcd2638c9b0a4a21982f4db832d50","last_reissued_at":"2026-07-05T01:56:56.969599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:56.969599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Refinement Feature Pyramid Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Jialiang Ma","submitted_at":"2020-12-03T07:17:03Z","abstract_excerpt":"FPN is a common component used in object detectors, it supplements multi-scale information by adjacent level features interpolation and summation. However, due to the existence of nonlinear operations and the convolutional layers with different output dimensions, the relationship between different levels is much more complex, the pixel-wise summation is not an efficient approach. In this paper, we first analyze the design defects from pixel level and feature map level. Then, we design a novel parameter-free feature pyramid networks named Dual Refinement Feature Pyramid Networks (DRFPN) for the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01733","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.01733/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2012.01733","created_at":"2026-07-05T01:56:56.969656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.01733v2","created_at":"2026-07-05T01:56:56.969656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01733","created_at":"2026-07-05T01:56:56.969656+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPES3ZR66YLL","created_at":"2026-07-05T01:56:56.969656+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPES3ZR66YLLD3TP","created_at":"2026-07-05T01:56:56.969656+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPES3ZR6","created_at":"2026-07-05T01:56:56.969656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13373","citing_title":"Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU","json":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU.json","graph_json":"https://pith.science/api/pith-number/JPES3ZR66YLLD3TPS7SDHWS3VU/graph.json","events_json":"https://pith.science/api/pith-number/JPES3ZR66YLLD3TPS7SDHWS3VU/events.json","paper":"https://pith.science/paper/JPES3ZR6"},"agent_actions":{"view_html":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU","download_json":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU.json","view_paper":"https://pith.science/paper/JPES3ZR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.01733&json=true","fetch_graph":"https://pith.science/api/pith-number/JPES3ZR66YLLD3TPS7SDHWS3VU/graph.json","fetch_events":"https://pith.science/api/pith-number/JPES3ZR66YLLD3TPS7SDHWS3VU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU/action/storage_attestation","attest_author":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU/action/author_attestation","sign_citation":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU/action/citation_signature","submit_replication":"https://pith.science/pith/JPES3ZR66YLLD3TPS7SDHWS3VU/action/replication_record"}},"created_at":"2026-07-05T01:56:56.969656+00:00","updated_at":"2026-07-05T01:56:56.969656+00:00"}