{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N65V7MHR4K5FMKRESGN6Q6HSZ3","short_pith_number":"pith:N65V7MHR","schema_version":"1.0","canonical_sha256":"6fbb5fb0f1e2ba562a24919be878f2cee78823e9b7dad9a4dc561efe60700baa","source":{"kind":"arxiv","id":"2411.09453","version":1},"attestation_state":"computed","paper":{"title":"Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen-Long Duan, Lin Zhao, Xiu-Shen Wei, Yong Li","submitted_at":"2024-11-14T13:59:01Z","abstract_excerpt":"Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model parameters, often fall short when confronted with long-tailed distributions, especially in detection tasks. This is largely due to extreme data imbalance and the issue of simplicity bias. In this paper, we introduce a novel pre-training framework for object detection, called Dynamic Rebalancing Contrastive Learning with Dual Reconstruction (2DRCL). Our metho"},"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":"2411.09453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T13:59:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a8eecd2942b66a4d4b97ffbb1b34577fdd1fab7bd3fe528a372b6312cfe04e34","abstract_canon_sha256":"01f73411a9ac03646bf89e4872c988d00ade8007c0dd88c1ddd4e884f401e555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:27.207580Z","signature_b64":"7/DVVcY9ckVzJ9Oyfv9bYEWV4qQJgUC+26WXXJayOwZV3+wmpFUlsLM0ADLH79AyvXLfgZQczGIcaGv0+j5nCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fbb5fb0f1e2ba562a24919be878f2cee78823e9b7dad9a4dc561efe60700baa","last_reissued_at":"2026-07-05T09:35:27.207095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:27.207095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen-Long Duan, Lin Zhao, Xiu-Shen Wei, Yong Li","submitted_at":"2024-11-14T13:59:01Z","abstract_excerpt":"Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model parameters, often fall short when confronted with long-tailed distributions, especially in detection tasks. This is largely due to extreme data imbalance and the issue of simplicity bias. In this paper, we introduce a novel pre-training framework for object detection, called Dynamic Rebalancing Contrastive Learning with Dual Reconstruction (2DRCL). Our metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09453","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/2411.09453/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":"2411.09453","created_at":"2026-07-05T09:35:27.207151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09453v1","created_at":"2026-07-05T09:35:27.207151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09453","created_at":"2026-07-05T09:35:27.207151+00:00"},{"alias_kind":"pith_short_12","alias_value":"N65V7MHR4K5F","created_at":"2026-07-05T09:35:27.207151+00:00"},{"alias_kind":"pith_short_16","alias_value":"N65V7MHR4K5FMKRE","created_at":"2026-07-05T09:35:27.207151+00:00"},{"alias_kind":"pith_short_8","alias_value":"N65V7MHR","created_at":"2026-07-05T09:35:27.207151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3","json":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3.json","graph_json":"https://pith.science/api/pith-number/N65V7MHR4K5FMKRESGN6Q6HSZ3/graph.json","events_json":"https://pith.science/api/pith-number/N65V7MHR4K5FMKRESGN6Q6HSZ3/events.json","paper":"https://pith.science/paper/N65V7MHR"},"agent_actions":{"view_html":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3","download_json":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3.json","view_paper":"https://pith.science/paper/N65V7MHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09453&json=true","fetch_graph":"https://pith.science/api/pith-number/N65V7MHR4K5FMKRESGN6Q6HSZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/N65V7MHR4K5FMKRESGN6Q6HSZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3/action/storage_attestation","attest_author":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3/action/author_attestation","sign_citation":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3/action/citation_signature","submit_replication":"https://pith.science/pith/N65V7MHR4K5FMKRESGN6Q6HSZ3/action/replication_record"}},"created_at":"2026-07-05T09:35:27.207151+00:00","updated_at":"2026-07-05T09:35:27.207151+00:00"}