{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RCEDSOMG4ILHNXIME7HBTW65JO","short_pith_number":"pith:RCEDSOMG","schema_version":"1.0","canonical_sha256":"8888393986e21676dd0c27ce19dbdd4ba09f4646e1b93a5c4a74bef84dc15069","source":{"kind":"arxiv","id":"1603.08695","version":2},"attestation_state":"computed","paper":{"title":"Learning to Refine Object Segments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pedro O. Pinheiro, Piotr Doll\\`ar, Ronan Collobert, Tsung-Yi Lin","submitted_at":"2016-03-29T09:33:44Z","abstract_excerpt":"Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode object-level knowledge but are invariant to factors such as pose and appearance. In this work we propose to augment feedforward nets for object segmentation with a novel top-down refinement approach. The resulting bottom-up/top-down architecture is capable of efficiently generating high-fidelity object masks. Similarly to skip connections, our approach leverages fea"},"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":"1603.08695","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-29T09:33:44Z","cross_cats_sorted":[],"title_canon_sha256":"ce1f22c1b6d18835ec8b3621fb6ab295b12882a962919859b95c8ab5d116138b","abstract_canon_sha256":"f180fb01674c8f671387e521c9d958828dd90a5aa6d848292c79cf2cbf0bdcb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:23.380057Z","signature_b64":"kv/BW5GdK/RoyBNbmTFaAlZVf7nkS5AthwD2RCoHlaIy4QLdMi1PWkrxrbXW9Bhc24PC2PoaaYZjejMsaJQrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8888393986e21676dd0c27ce19dbdd4ba09f4646e1b93a5c4a74bef84dc15069","last_reissued_at":"2026-05-18T01:10:23.379615Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:23.379615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Refine Object Segments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pedro O. Pinheiro, Piotr Doll\\`ar, Ronan Collobert, Tsung-Yi Lin","submitted_at":"2016-03-29T09:33:44Z","abstract_excerpt":"Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode object-level knowledge but are invariant to factors such as pose and appearance. In this work we propose to augment feedforward nets for object segmentation with a novel top-down refinement approach. The resulting bottom-up/top-down architecture is capable of efficiently generating high-fidelity object masks. Similarly to skip connections, our approach leverages fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08695","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":"1603.08695","created_at":"2026-05-18T01:10:23.379700+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.08695v2","created_at":"2026-05-18T01:10:23.379700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08695","created_at":"2026-05-18T01:10:23.379700+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCEDSOMG4ILH","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCEDSOMG4ILHNXIM","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCEDSOMG","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04444","citing_title":"A review on deep learning techniques for 3D sensed data classification","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO","json":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO.json","graph_json":"https://pith.science/api/pith-number/RCEDSOMG4ILHNXIME7HBTW65JO/graph.json","events_json":"https://pith.science/api/pith-number/RCEDSOMG4ILHNXIME7HBTW65JO/events.json","paper":"https://pith.science/paper/RCEDSOMG"},"agent_actions":{"view_html":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO","download_json":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO.json","view_paper":"https://pith.science/paper/RCEDSOMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.08695&json=true","fetch_graph":"https://pith.science/api/pith-number/RCEDSOMG4ILHNXIME7HBTW65JO/graph.json","fetch_events":"https://pith.science/api/pith-number/RCEDSOMG4ILHNXIME7HBTW65JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO/action/storage_attestation","attest_author":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO/action/author_attestation","sign_citation":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO/action/citation_signature","submit_replication":"https://pith.science/pith/RCEDSOMG4ILHNXIME7HBTW65JO/action/replication_record"}},"created_at":"2026-05-18T01:10:23.379700+00:00","updated_at":"2026-05-18T01:10:23.379700+00:00"}