{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SLOEFSRCSSFO2S73MHUW6QISUY","short_pith_number":"pith:SLOEFSRC","schema_version":"1.0","canonical_sha256":"92dc42ca22948aed4bfb61e96f4112a6197e820470765bdd52457b00e35ed866","source":{"kind":"arxiv","id":"2308.06412","version":3},"attestation_state":"computed","paper":{"title":"Taming Self-Training for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Long Zhao, Manmohan Chandraker, Samuel Schulter, Shiyu Zhao, Vijay Kumar B.G, Yumin Suh, Zhixing Zhang","submitted_at":"2023-08-11T23:03:50Z","abstract_excerpt":"Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). However, teacher-student self-training, a powerful and widely used paradigm to leverage PLs, is rarely explored for OVD. This work identifies two challenges of using self-training in OVD: noisy PLs from VLMs and frequent distribution changes of PLs. To address these challenges, we propose SAS-Det that tames self-training for OVD from two key perspectives. First, we present a split-and-fusion (SAF) head that splits a standa"},"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":"2308.06412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-11T23:03:50Z","cross_cats_sorted":[],"title_canon_sha256":"1939e52e52599d46be4fd53e946e8ce93404753f9c437bdb59e328d62e180acf","abstract_canon_sha256":"326e49111b05c506638ce657d780a84ef811ef43a360b1edeb0275d37f4c54ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:28.820463Z","signature_b64":"QneO4Jp6jRKvsQqavoucsYoyNadwW4u58e0cPrH8Fh/8ppA0QZRcEAl1R0ng9L+pLR3i1YjLFh3r3I1uIYVxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92dc42ca22948aed4bfb61e96f4112a6197e820470765bdd52457b00e35ed866","last_reissued_at":"2026-07-05T08:07:28.819985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:28.819985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming Self-Training for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Long Zhao, Manmohan Chandraker, Samuel Schulter, Shiyu Zhao, Vijay Kumar B.G, Yumin Suh, Zhixing Zhang","submitted_at":"2023-08-11T23:03:50Z","abstract_excerpt":"Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). However, teacher-student self-training, a powerful and widely used paradigm to leverage PLs, is rarely explored for OVD. This work identifies two challenges of using self-training in OVD: noisy PLs from VLMs and frequent distribution changes of PLs. To address these challenges, we propose SAS-Det that tames self-training for OVD from two key perspectives. First, we present a split-and-fusion (SAF) head that splits a standa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06412","kind":"arxiv","version":3},"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/2308.06412/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":"2308.06412","created_at":"2026-07-05T08:07:28.820043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06412v3","created_at":"2026-07-05T08:07:28.820043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06412","created_at":"2026-07-05T08:07:28.820043+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLOEFSRCSSFO","created_at":"2026-07-05T08:07:28.820043+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLOEFSRCSSFO2S73","created_at":"2026-07-05T08:07:28.820043+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLOEFSRC","created_at":"2026-07-05T08:07:28.820043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01008","citing_title":"ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY","json":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY.json","graph_json":"https://pith.science/api/pith-number/SLOEFSRCSSFO2S73MHUW6QISUY/graph.json","events_json":"https://pith.science/api/pith-number/SLOEFSRCSSFO2S73MHUW6QISUY/events.json","paper":"https://pith.science/paper/SLOEFSRC"},"agent_actions":{"view_html":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY","download_json":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY.json","view_paper":"https://pith.science/paper/SLOEFSRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06412&json=true","fetch_graph":"https://pith.science/api/pith-number/SLOEFSRCSSFO2S73MHUW6QISUY/graph.json","fetch_events":"https://pith.science/api/pith-number/SLOEFSRCSSFO2S73MHUW6QISUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY/action/storage_attestation","attest_author":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY/action/author_attestation","sign_citation":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY/action/citation_signature","submit_replication":"https://pith.science/pith/SLOEFSRCSSFO2S73MHUW6QISUY/action/replication_record"}},"created_at":"2026-07-05T08:07:28.820043+00:00","updated_at":"2026-07-05T08:07:28.820043+00:00"}