{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GPMIGZXN4MEUNML3H5SH3DD5FK","short_pith_number":"pith:GPMIGZXN","schema_version":"1.0","canonical_sha256":"33d88366ede30946b17b3f647d8c7d2a99a36076bede433707ef6d2bc0e85821","source":{"kind":"arxiv","id":"2312.14494","version":4},"attestation_state":"computed","paper":{"title":"Revisiting Few-Shot Object Detection with Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anish Madan, Deva Ramanan, Neehar Peri, Shu Kong","submitted_at":"2023-12-22T07:42:00Z","abstract_excerpt":"The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of \"open-world\" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent foundational VLMs. First, we point out that zero-shot predictions from VLMs such as GroundingDINO significantly outperform state-of-the-art few-shot detectors (48 vs. 33 AP) on COCO. Despite their strong zero-shot performance, such foundation models may still be sub-optimal. For example, trucks on the web may be defined differently from trucks for a target applicatio"},"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":"2312.14494","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T07:42:00Z","cross_cats_sorted":[],"title_canon_sha256":"427e67f736dfc96a2b7be333fe570de029148d1c2f509ba2018e7252f45845c3","abstract_canon_sha256":"f0bb1233b23a965f31cbafbb08ee33d871d95748d68e76b7ddc6de1a56a250ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:53.443525Z","signature_b64":"dfkXeAPz39YvDeWCsdH1gI50TMc80ymcrvWMwZUDxOEEf+OtU+OoE1IJdUkACfdAeg3uJI3gKy+4AVVPUyYXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33d88366ede30946b17b3f647d8c7d2a99a36076bede433707ef6d2bc0e85821","last_reissued_at":"2026-07-05T09:19:53.443122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:53.443122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Few-Shot Object Detection with Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anish Madan, Deva Ramanan, Neehar Peri, Shu Kong","submitted_at":"2023-12-22T07:42:00Z","abstract_excerpt":"The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of \"open-world\" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent foundational VLMs. First, we point out that zero-shot predictions from VLMs such as GroundingDINO significantly outperform state-of-the-art few-shot detectors (48 vs. 33 AP) on COCO. Despite their strong zero-shot performance, such foundation models may still be sub-optimal. For example, trucks on the web may be defined differently from trucks for a target applicatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14494","kind":"arxiv","version":4},"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/2312.14494/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":"2312.14494","created_at":"2026-07-05T09:19:53.443177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14494v4","created_at":"2026-07-05T09:19:53.443177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14494","created_at":"2026-07-05T09:19:53.443177+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPMIGZXN4MEU","created_at":"2026-07-05T09:19:53.443177+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPMIGZXN4MEUNML3","created_at":"2026-07-05T09:19:53.443177+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPMIGZXN","created_at":"2026-07-05T09:19:53.443177+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/GPMIGZXN4MEUNML3H5SH3DD5FK","json":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK.json","graph_json":"https://pith.science/api/pith-number/GPMIGZXN4MEUNML3H5SH3DD5FK/graph.json","events_json":"https://pith.science/api/pith-number/GPMIGZXN4MEUNML3H5SH3DD5FK/events.json","paper":"https://pith.science/paper/GPMIGZXN"},"agent_actions":{"view_html":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK","download_json":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK.json","view_paper":"https://pith.science/paper/GPMIGZXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14494&json=true","fetch_graph":"https://pith.science/api/pith-number/GPMIGZXN4MEUNML3H5SH3DD5FK/graph.json","fetch_events":"https://pith.science/api/pith-number/GPMIGZXN4MEUNML3H5SH3DD5FK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK/action/storage_attestation","attest_author":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK/action/author_attestation","sign_citation":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK/action/citation_signature","submit_replication":"https://pith.science/pith/GPMIGZXN4MEUNML3H5SH3DD5FK/action/replication_record"}},"created_at":"2026-07-05T09:19:53.443177+00:00","updated_at":"2026-07-05T09:19:53.443177+00:00"}