{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LCKHMWIHJ7FQI27LU6HWTAF3HF","short_pith_number":"pith:LCKHMWIH","schema_version":"1.0","canonical_sha256":"58947659074fcb046beba78f6980bb3957daeb5636b71d64b970fe9515fbd211","source":{"kind":"arxiv","id":"2103.14259","version":1},"attestation_state":"computed","paper":{"title":"OTA: Optimal Transport Assignment for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Osamu Yoshie, Songtao Liu, Zeming Li, Zheng Ge","submitted_at":"2021-03-26T04:45:12Z","abstract_excerpt":"Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object. In this paper, we innovatively revisit the label assignment from a global perspective and propose to formulate the assigning procedure as an Optimal Transport (OT) problem -- a well-studied topic in Optimization Theory. Concretely, we define the unit transportation cost between each demander (anchor) and supplier (gt) pair as the weighted summation of their classification and regression losses. After formulation, finding the best assi"},"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":"2103.14259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-26T04:45:12Z","cross_cats_sorted":[],"title_canon_sha256":"d931e87066d8712a5f9aa6890d47562493f0377d93ed444abd4da01b57049ae0","abstract_canon_sha256":"2e42cd2c726ca50fb23c096f9402ef5999dac75d966781b2b0bdca1d0950aa3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:32.075971Z","signature_b64":"JsVlr4x1zdTkTblLwKMKNKZDPUITLX5MWLQJ4XAgn4o96UltFsDqBEp8xxRq1L06bxZVblzRgCFyF2lK4e9aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58947659074fcb046beba78f6980bb3957daeb5636b71d64b970fe9515fbd211","last_reissued_at":"2026-07-05T02:26:32.075481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:32.075481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OTA: Optimal Transport Assignment for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Osamu Yoshie, Songtao Liu, Zeming Li, Zheng Ge","submitted_at":"2021-03-26T04:45:12Z","abstract_excerpt":"Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object. In this paper, we innovatively revisit the label assignment from a global perspective and propose to formulate the assigning procedure as an Optimal Transport (OT) problem -- a well-studied topic in Optimization Theory. Concretely, we define the unit transportation cost between each demander (anchor) and supplier (gt) pair as the weighted summation of their classification and regression losses. After formulation, finding the best assi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14259","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/2103.14259/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":"2103.14259","created_at":"2026-07-05T02:26:32.075537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14259v1","created_at":"2026-07-05T02:26:32.075537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14259","created_at":"2026-07-05T02:26:32.075537+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCKHMWIHJ7FQ","created_at":"2026-07-05T02:26:32.075537+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCKHMWIHJ7FQI27L","created_at":"2026-07-05T02:26:32.075537+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCKHMWIH","created_at":"2026-07-05T02:26:32.075537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11738","citing_title":"WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF","json":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF.json","graph_json":"https://pith.science/api/pith-number/LCKHMWIHJ7FQI27LU6HWTAF3HF/graph.json","events_json":"https://pith.science/api/pith-number/LCKHMWIHJ7FQI27LU6HWTAF3HF/events.json","paper":"https://pith.science/paper/LCKHMWIH"},"agent_actions":{"view_html":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF","download_json":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF.json","view_paper":"https://pith.science/paper/LCKHMWIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14259&json=true","fetch_graph":"https://pith.science/api/pith-number/LCKHMWIHJ7FQI27LU6HWTAF3HF/graph.json","fetch_events":"https://pith.science/api/pith-number/LCKHMWIHJ7FQI27LU6HWTAF3HF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF/action/storage_attestation","attest_author":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF/action/author_attestation","sign_citation":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF/action/citation_signature","submit_replication":"https://pith.science/pith/LCKHMWIHJ7FQI27LU6HWTAF3HF/action/replication_record"}},"created_at":"2026-07-05T02:26:32.075537+00:00","updated_at":"2026-07-05T02:26:32.075537+00:00"}