{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RM74O2TZY35A5H4WBFUXIS7HJ4","short_pith_number":"pith:RM74O2TZ","schema_version":"1.0","canonical_sha256":"8b3fc76a79c6fa0e9f960969744be74f12d56253f99ab0e4cf00b1ad97a59053","source":{"kind":"arxiv","id":"1908.09075","version":1},"attestation_state":"computed","paper":{"title":"Residual Objectness for Imbalance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Dong Liu, Enhong Chen, Joya Chen, Tong Xu, Xuezheng Peng","submitted_at":"2019-08-24T02:24:25Z","abstract_excerpt":"For a long time, object detectors have suffered from extreme imbalance between foregrounds and backgrounds. While several sampling/reweighting schemes have been explored to alleviate the imbalance, they are usually heuristic and demand laborious hyper-parameters tuning, which is hard to achieve the optimality. In this paper, we first reveal that such the imbalance could be addressed in a learning-based manner. Guided by this illuminating observation, we propose a novel Residual Objectness (ResObj) mechanism that addresses the imbalance by end-to-end optimization, while no further hand-crafted "},"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":"1908.09075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-24T02:24:25Z","cross_cats_sorted":[],"title_canon_sha256":"0fb3aab0df58c86d4c43a5dd088f6630703ce344d61a74b994a8b0c3c6606dd6","abstract_canon_sha256":"a31faa140957bfc48402b061839d79102fa6df7566e51b891284ac7d6a907155"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:36.557867Z","signature_b64":"HlkV5ijDkdpiOeXPdJpapy0cWMZyw0DLWYhX1p38BeuxYcDDOiEKkYt0XumNWLcTY0NRusnrb0gD8U3P5g8ZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3fc76a79c6fa0e9f960969744be74f12d56253f99ab0e4cf00b1ad97a59053","last_reissued_at":"2026-07-04T23:59:36.557421Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:36.557421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual Objectness for Imbalance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Dong Liu, Enhong Chen, Joya Chen, Tong Xu, Xuezheng Peng","submitted_at":"2019-08-24T02:24:25Z","abstract_excerpt":"For a long time, object detectors have suffered from extreme imbalance between foregrounds and backgrounds. While several sampling/reweighting schemes have been explored to alleviate the imbalance, they are usually heuristic and demand laborious hyper-parameters tuning, which is hard to achieve the optimality. In this paper, we first reveal that such the imbalance could be addressed in a learning-based manner. Guided by this illuminating observation, we propose a novel Residual Objectness (ResObj) mechanism that addresses the imbalance by end-to-end optimization, while no further hand-crafted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09075","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.09075/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":"1908.09075","created_at":"2026-07-04T23:59:36.557478+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09075v1","created_at":"2026-07-04T23:59:36.557478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09075","created_at":"2026-07-04T23:59:36.557478+00:00"},{"alias_kind":"pith_short_12","alias_value":"RM74O2TZY35A","created_at":"2026-07-04T23:59:36.557478+00:00"},{"alias_kind":"pith_short_16","alias_value":"RM74O2TZY35A5H4W","created_at":"2026-07-04T23:59:36.557478+00:00"},{"alias_kind":"pith_short_8","alias_value":"RM74O2TZ","created_at":"2026-07-04T23:59:36.557478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.00169","citing_title":"Imbalance Problems in Object Detection: A Review","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4","json":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4.json","graph_json":"https://pith.science/api/pith-number/RM74O2TZY35A5H4WBFUXIS7HJ4/graph.json","events_json":"https://pith.science/api/pith-number/RM74O2TZY35A5H4WBFUXIS7HJ4/events.json","paper":"https://pith.science/paper/RM74O2TZ"},"agent_actions":{"view_html":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4","download_json":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4.json","view_paper":"https://pith.science/paper/RM74O2TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09075&json=true","fetch_graph":"https://pith.science/api/pith-number/RM74O2TZY35A5H4WBFUXIS7HJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/RM74O2TZY35A5H4WBFUXIS7HJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4/action/storage_attestation","attest_author":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4/action/author_attestation","sign_citation":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4/action/citation_signature","submit_replication":"https://pith.science/pith/RM74O2TZY35A5H4WBFUXIS7HJ4/action/replication_record"}},"created_at":"2026-07-04T23:59:36.557478+00:00","updated_at":"2026-07-04T23:59:36.557478+00:00"}