{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U55RQUKD6UC3NJRLZ6ZWHWSNGU","short_pith_number":"pith:U55RQUKD","schema_version":"1.0","canonical_sha256":"a77b185143f505b6a62bcfb363da4d3520a19c7591bd4a9c66bfa007ca1f275d","source":{"kind":"arxiv","id":"2404.01819","version":1},"attestation_state":"computed","paper":{"title":"Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Khurram Azeem Hashmi, Muhammad Zeshan Afzal, Tahira Shehzadi","submitted_at":"2024-04-02T10:22:23Z","abstract_excerpt":"In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of object queries. In DETR-based SSOD, the one-to-one assignment strategy provides inaccurate pseudo-labels, while the one-to-many assignments strategy leads to overlapping predictions. These issues compromise training efficiency and degrade model performance, especially in detecting small or occluded objects. We introduce Sparse Semi-DETR, a novel transformer-based, end-to-end semi-supervised object detection solution to ov"},"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":"2404.01819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T10:22:23Z","cross_cats_sorted":[],"title_canon_sha256":"14e2d5975f9f7f6ec87ca21110d4f127526ea253cf592f394c5bcb541ea02b6e","abstract_canon_sha256":"de587b614c88cf926e2554ead74ba79bd5883d0efbf4d9b091473ba5729ed3b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:31.875998Z","signature_b64":"1nOTqUnpZuUofLYc29jJYNlwxF0FfC2y3/28rmPnxxFZbRNUjXQ8g2cWG8kfhX/tGiDmaX+2vHQPNjzBk79rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77b185143f505b6a62bcfb363da4d3520a19c7591bd4a9c66bfa007ca1f275d","last_reissued_at":"2026-07-05T08:03:31.875586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:31.875586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Khurram Azeem Hashmi, Muhammad Zeshan Afzal, Tahira Shehzadi","submitted_at":"2024-04-02T10:22:23Z","abstract_excerpt":"In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of object queries. In DETR-based SSOD, the one-to-one assignment strategy provides inaccurate pseudo-labels, while the one-to-many assignments strategy leads to overlapping predictions. These issues compromise training efficiency and degrade model performance, especially in detecting small or occluded objects. We introduce Sparse Semi-DETR, a novel transformer-based, end-to-end semi-supervised object detection solution to ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01819","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/2404.01819/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":"2404.01819","created_at":"2026-07-05T08:03:31.875638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01819v1","created_at":"2026-07-05T08:03:31.875638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01819","created_at":"2026-07-05T08:03:31.875638+00:00"},{"alias_kind":"pith_short_12","alias_value":"U55RQUKD6UC3","created_at":"2026-07-05T08:03:31.875638+00:00"},{"alias_kind":"pith_short_16","alias_value":"U55RQUKD6UC3NJRL","created_at":"2026-07-05T08:03:31.875638+00:00"},{"alias_kind":"pith_short_8","alias_value":"U55RQUKD","created_at":"2026-07-05T08:03:31.875638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00374","citing_title":"LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Image","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU","json":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU.json","graph_json":"https://pith.science/api/pith-number/U55RQUKD6UC3NJRLZ6ZWHWSNGU/graph.json","events_json":"https://pith.science/api/pith-number/U55RQUKD6UC3NJRLZ6ZWHWSNGU/events.json","paper":"https://pith.science/paper/U55RQUKD"},"agent_actions":{"view_html":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU","download_json":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU.json","view_paper":"https://pith.science/paper/U55RQUKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01819&json=true","fetch_graph":"https://pith.science/api/pith-number/U55RQUKD6UC3NJRLZ6ZWHWSNGU/graph.json","fetch_events":"https://pith.science/api/pith-number/U55RQUKD6UC3NJRLZ6ZWHWSNGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU/action/storage_attestation","attest_author":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU/action/author_attestation","sign_citation":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU/action/citation_signature","submit_replication":"https://pith.science/pith/U55RQUKD6UC3NJRLZ6ZWHWSNGU/action/replication_record"}},"created_at":"2026-07-05T08:03:31.875638+00:00","updated_at":"2026-07-05T08:03:31.875638+00:00"}