{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NFGZX2LQOOHD5QGIXUYZ6BSBUS","short_pith_number":"pith:NFGZX2LQ","schema_version":"1.0","canonical_sha256":"694d9be970738e3ec0c8bd319f0641a48acb6784a1e5b521d11656527bd61826","source":{"kind":"arxiv","id":"1612.03144","version":2},"attestation_state":"computed","paper":{"title":"Feature Pyramid Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Kaiming He, Piotr Doll\\'ar, Ross Girshick, Serge Belongie, Tsung-Yi Lin","submitted_at":"2016-12-09T19:55:54Z","abstract_excerpt":"Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant i"},"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":"1612.03144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-09T19:55:54Z","cross_cats_sorted":[],"title_canon_sha256":"0913f2e80479ee2d65eec352071858b42b3bae3ec68795db8f2924bce429bfc5","abstract_canon_sha256":"30a4008c9b1dba2b407bea2c6562f8ae3057cb7eb874c655323ceaed11805871"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:04.207503Z","signature_b64":"5nY8Fl1KVuD7yWpFAuHnuYgw8w3VsTSI3UKN/wMEsko6Uux9yDmI9lb5BTPlMe6It90cedvpnMuXcrJbKngNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694d9be970738e3ec0c8bd319f0641a48acb6784a1e5b521d11656527bd61826","last_reissued_at":"2026-05-18T00:46:04.206863Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:04.206863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Pyramid Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Kaiming He, Piotr Doll\\'ar, Ross Girshick, Serge Belongie, Tsung-Yi Lin","submitted_at":"2016-12-09T19:55:54Z","abstract_excerpt":"Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03144","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":""},"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":"1612.03144","created_at":"2026-05-18T00:46:04.206977+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.03144v2","created_at":"2026-05-18T00:46:04.206977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03144","created_at":"2026-05-18T00:46:04.206977+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFGZX2LQOOHD","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFGZX2LQOOHD5QGI","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFGZX2LQ","created_at":"2026-05-18T12:30:32.724797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.09266","citing_title":"A Multitask Network for Localization and Recognition of Text in Images","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10473","citing_title":"Switchable Normalization for Learning-to-Normalize Deep Representation","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2602.23024","citing_title":"InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2001.10773","citing_title":"Virtual KITTI 2","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13278","citing_title":"DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11081","citing_title":"MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS","json":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS.json","graph_json":"https://pith.science/api/pith-number/NFGZX2LQOOHD5QGIXUYZ6BSBUS/graph.json","events_json":"https://pith.science/api/pith-number/NFGZX2LQOOHD5QGIXUYZ6BSBUS/events.json","paper":"https://pith.science/paper/NFGZX2LQ"},"agent_actions":{"view_html":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS","download_json":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS.json","view_paper":"https://pith.science/paper/NFGZX2LQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.03144&json=true","fetch_graph":"https://pith.science/api/pith-number/NFGZX2LQOOHD5QGIXUYZ6BSBUS/graph.json","fetch_events":"https://pith.science/api/pith-number/NFGZX2LQOOHD5QGIXUYZ6BSBUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS/action/storage_attestation","attest_author":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS/action/author_attestation","sign_citation":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS/action/citation_signature","submit_replication":"https://pith.science/pith/NFGZX2LQOOHD5QGIXUYZ6BSBUS/action/replication_record"}},"created_at":"2026-05-18T00:46:04.206977+00:00","updated_at":"2026-05-18T00:46:04.206977+00:00"}