{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PFWT34WQ4KR7RSCPUMI5TAZDMS","short_pith_number":"pith:PFWT34WQ","schema_version":"1.0","canonical_sha256":"796d3df2d0e2a3f8c84fa311d9832364b53af3485515a1017864458d2abbb19f","source":{"kind":"arxiv","id":"2211.12860","version":6},"attestation_state":"computed","paper":{"title":"DETRs with Collaborative Hybrid Assignments Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Yu Liu, Zhuofan Zong","submitted_at":"2022-11-22T16:19:52Z","abstract_excerpt":"In this paper, we provide the observation that too few queries assigned as positive samples in DETR with one-to-one set matching leads to sparse supervision on the encoder's output which considerably hurt the discriminative feature learning of the encoder and vice visa for attention learning in the decoder. To alleviate this, we present a novel collaborative hybrid assignments training scheme, namely $\\mathcal{C}$o-DETR, to learn more efficient and effective DETR-based detectors from versatile label assignment manners. This new training scheme can easily enhance the encoder's learning ability "},"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":"2211.12860","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T16:19:52Z","cross_cats_sorted":[],"title_canon_sha256":"c3e72206edf6e7509ce3411aee37daa382dc0a8f95ae289846742fca5c9bcc84","abstract_canon_sha256":"76696316036a98881993c8d4acd20b3068d30c4052646c52486d9aaf14e2c227"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:46.307498Z","signature_b64":"7urJsngjcjwELvDv5r+54sdEkkDDyuu+1wO6ZXGop3pbod8KqkFg+5fUaft07wpdf1zItRUFD8fDKGSlvFwoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796d3df2d0e2a3f8c84fa311d9832364b53af3485515a1017864458d2abbb19f","last_reissued_at":"2026-07-05T06:41:46.307034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:46.307034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DETRs with Collaborative Hybrid Assignments Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Yu Liu, Zhuofan Zong","submitted_at":"2022-11-22T16:19:52Z","abstract_excerpt":"In this paper, we provide the observation that too few queries assigned as positive samples in DETR with one-to-one set matching leads to sparse supervision on the encoder's output which considerably hurt the discriminative feature learning of the encoder and vice visa for attention learning in the decoder. To alleviate this, we present a novel collaborative hybrid assignments training scheme, namely $\\mathcal{C}$o-DETR, to learn more efficient and effective DETR-based detectors from versatile label assignment manners. This new training scheme can easily enhance the encoder's learning ability "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12860","kind":"arxiv","version":6},"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/2211.12860/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":"2211.12860","created_at":"2026-07-05T06:41:46.307085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12860v6","created_at":"2026-07-05T06:41:46.307085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12860","created_at":"2026-07-05T06:41:46.307085+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFWT34WQ4KR7","created_at":"2026-07-05T06:41:46.307085+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFWT34WQ4KR7RSCP","created_at":"2026-07-05T06:41:46.307085+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFWT34WQ","created_at":"2026-07-05T06:41:46.307085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24508","citing_title":"FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21502","citing_title":"VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2305.07598","citing_title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2406.17323","citing_title":"XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21502","citing_title":"VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS","json":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS.json","graph_json":"https://pith.science/api/pith-number/PFWT34WQ4KR7RSCPUMI5TAZDMS/graph.json","events_json":"https://pith.science/api/pith-number/PFWT34WQ4KR7RSCPUMI5TAZDMS/events.json","paper":"https://pith.science/paper/PFWT34WQ"},"agent_actions":{"view_html":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS","download_json":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS.json","view_paper":"https://pith.science/paper/PFWT34WQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12860&json=true","fetch_graph":"https://pith.science/api/pith-number/PFWT34WQ4KR7RSCPUMI5TAZDMS/graph.json","fetch_events":"https://pith.science/api/pith-number/PFWT34WQ4KR7RSCPUMI5TAZDMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS/action/storage_attestation","attest_author":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS/action/author_attestation","sign_citation":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS/action/citation_signature","submit_replication":"https://pith.science/pith/PFWT34WQ4KR7RSCPUMI5TAZDMS/action/replication_record"}},"created_at":"2026-07-05T06:41:46.307085+00:00","updated_at":"2026-07-05T06:41:46.307085+00:00"}