{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WXBGPLZNIEVV4MDJAR6DITWT6O","short_pith_number":"pith:WXBGPLZN","schema_version":"1.0","canonical_sha256":"b5c267af2d412b5e3069047c344ed3f3b20fb35ebdb3874bd008ee7ef39627a5","source":{"kind":"arxiv","id":"2205.02101","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Sparse R-CNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Li, Fengming Liu, Ji Liu, Lu Tian, Qinghang Hong, Yi Shan","submitted_at":"2022-05-04T14:56:25Z","abstract_excerpt":"Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a one-to-one label assignment scheme, where the Hungarian algorithm is applied to match only one positive sample for each ground truth. Such one-to-one assignment may not be optimal for the matching between the learned proposal boxes and ground truths. To address this problem, we propose dynamic label assignment (DLA) based on the optimal transport algorithm to"},"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":"2205.02101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T14:56:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1f8fb88a75f3f2fff7021eb3980e677d1b4de9465db05e2da52b1daa83d9654c","abstract_canon_sha256":"3dcafe85d18d231424d3673b5cb9d3c60c73e7dc82c0d6f2a4ed1539d013d66e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:25.154507Z","signature_b64":"kt2LdaBKIbFmp6S9EbSZb218FUwhImF59ggEud80b2oZ6mzNhj124cbRDEzuc9G3k3nBiRZAfDHeMEx0iOwMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5c267af2d412b5e3069047c344ed3f3b20fb35ebdb3874bd008ee7ef39627a5","last_reissued_at":"2026-07-05T04:20:25.154154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:25.154154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Sparse R-CNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Li, Fengming Liu, Ji Liu, Lu Tian, Qinghang Hong, Yi Shan","submitted_at":"2022-05-04T14:56:25Z","abstract_excerpt":"Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a one-to-one label assignment scheme, where the Hungarian algorithm is applied to match only one positive sample for each ground truth. Such one-to-one assignment may not be optimal for the matching between the learned proposal boxes and ground truths. To address this problem, we propose dynamic label assignment (DLA) based on the optimal transport algorithm to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02101","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/2205.02101/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":"2205.02101","created_at":"2026-07-05T04:20:25.154211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.02101v1","created_at":"2026-07-05T04:20:25.154211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02101","created_at":"2026-07-05T04:20:25.154211+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXBGPLZNIEVV","created_at":"2026-07-05T04:20:25.154211+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXBGPLZNIEVV4MDJ","created_at":"2026-07-05T04:20:25.154211+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXBGPLZN","created_at":"2026-07-05T04:20:25.154211+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/WXBGPLZNIEVV4MDJAR6DITWT6O","json":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O.json","graph_json":"https://pith.science/api/pith-number/WXBGPLZNIEVV4MDJAR6DITWT6O/graph.json","events_json":"https://pith.science/api/pith-number/WXBGPLZNIEVV4MDJAR6DITWT6O/events.json","paper":"https://pith.science/paper/WXBGPLZN"},"agent_actions":{"view_html":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O","download_json":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O.json","view_paper":"https://pith.science/paper/WXBGPLZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.02101&json=true","fetch_graph":"https://pith.science/api/pith-number/WXBGPLZNIEVV4MDJAR6DITWT6O/graph.json","fetch_events":"https://pith.science/api/pith-number/WXBGPLZNIEVV4MDJAR6DITWT6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O/action/storage_attestation","attest_author":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O/action/author_attestation","sign_citation":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O/action/citation_signature","submit_replication":"https://pith.science/pith/WXBGPLZNIEVV4MDJAR6DITWT6O/action/replication_record"}},"created_at":"2026-07-05T04:20:25.154211+00:00","updated_at":"2026-07-05T04:20:25.154211+00:00"}