{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KONG6QI247JH3KYPNFAI2O7KXB","short_pith_number":"pith:KONG6QI2","schema_version":"1.0","canonical_sha256":"539a6f411ae7d27dab0f69408d3beab8513d63eb236fa1184c3b33609970404f","source":{"kind":"arxiv","id":"2209.15639","version":2},"attestation_state":"computed","paper":{"title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Weicheng Kuo, Xiuye Gu, Yin Cui","submitted_at":"2022-09-30T17:59:52Z","abstract_excerpt":"We present F-VLM, a simple open-vocabulary object detection method built upon Frozen Vision and Language Models. F-VLM simplifies the current multi-stage training pipeline by eliminating the need for knowledge distillation or detection-tailored pretraining. Surprisingly, we observe that a frozen VLM: 1) retains the locality-sensitive features necessary for detection, and 2) is a strong region classifier. We finetune only the detector head and combine the detector and VLM outputs for each region at inference time. F-VLM shows compelling scaling behavior and achieves +6.5 mask AP improvement ove"},"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":"2209.15639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"fd0a2400c54fdb8019868f4caaebd331d55e6024951ffcfcc6c2cf61cc897f4e","abstract_canon_sha256":"c28fdc8687ac7ac8c8caf9934ee06438e0262e11eb429e3e59e193b662888121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:05.187261Z","signature_b64":"y0Ss6T+SoTdnFgmslRz5i8AlQ6jTcomN81Wggcyn9J9TVvQohjcrInXRauP7boaPtESbGwxK36kTfg8YwBD3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"539a6f411ae7d27dab0f69408d3beab8513d63eb236fa1184c3b33609970404f","last_reissued_at":"2026-07-05T05:45:05.186818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:05.186818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Weicheng Kuo, Xiuye Gu, Yin Cui","submitted_at":"2022-09-30T17:59:52Z","abstract_excerpt":"We present F-VLM, a simple open-vocabulary object detection method built upon Frozen Vision and Language Models. F-VLM simplifies the current multi-stage training pipeline by eliminating the need for knowledge distillation or detection-tailored pretraining. Surprisingly, we observe that a frozen VLM: 1) retains the locality-sensitive features necessary for detection, and 2) is a strong region classifier. We finetune only the detector head and combine the detector and VLM outputs for each region at inference time. F-VLM shows compelling scaling behavior and achieves +6.5 mask AP improvement ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15639","kind":"arxiv","version":2},"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/2209.15639/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":"2209.15639","created_at":"2026-07-05T05:45:05.186878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15639v2","created_at":"2026-07-05T05:45:05.186878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15639","created_at":"2026-07-05T05:45:05.186878+00:00"},{"alias_kind":"pith_short_12","alias_value":"KONG6QI247JH","created_at":"2026-07-05T05:45:05.186878+00:00"},{"alias_kind":"pith_short_16","alias_value":"KONG6QI247JH3KYP","created_at":"2026-07-05T05:45:05.186878+00:00"},{"alias_kind":"pith_short_8","alias_value":"KONG6QI2","created_at":"2026-07-05T05:45:05.186878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09360","citing_title":"ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06978","citing_title":"CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05916","citing_title":"Unveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27116","citing_title":"COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28271","citing_title":"LV-OSD: Language-Vision-Complementary Open-Set Object Detection","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2410.10238","citing_title":"ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22394","citing_title":"Vision Transformers Need More Than Registers","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25383","citing_title":"CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB","json":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB.json","graph_json":"https://pith.science/api/pith-number/KONG6QI247JH3KYPNFAI2O7KXB/graph.json","events_json":"https://pith.science/api/pith-number/KONG6QI247JH3KYPNFAI2O7KXB/events.json","paper":"https://pith.science/paper/KONG6QI2"},"agent_actions":{"view_html":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB","download_json":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB.json","view_paper":"https://pith.science/paper/KONG6QI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15639&json=true","fetch_graph":"https://pith.science/api/pith-number/KONG6QI247JH3KYPNFAI2O7KXB/graph.json","fetch_events":"https://pith.science/api/pith-number/KONG6QI247JH3KYPNFAI2O7KXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB/action/storage_attestation","attest_author":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB/action/author_attestation","sign_citation":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB/action/citation_signature","submit_replication":"https://pith.science/pith/KONG6QI247JH3KYPNFAI2O7KXB/action/replication_record"}},"created_at":"2026-07-05T05:45:05.186878+00:00","updated_at":"2026-07-05T05:45:05.186878+00:00"}