{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IK5LTDLOGHHJGI6YUMZS7GXTPJ","short_pith_number":"pith:IK5LTDLO","schema_version":"1.0","canonical_sha256":"42bab98d6e31ce9323d8a3332f9af37a72c22e3a4efb3c3c207d13b85d79476e","source":{"kind":"arxiv","id":"2407.01400","version":2},"attestation_state":"computed","paper":{"title":"GalLoP: Learning Global and Local Prompts for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Elias Ramzi, Marc Lafon, Nicolas Audebert, Nicolas Thome","submitted_at":"2024-07-01T15:50:15Z","abstract_excerpt":"Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs), e.g. CLIP, for few-shot image classification. Despite their success, most prompt learning methods trade-off between classification accuracy and robustness, e.g. in domain generalization or out-of-distribution (OOD) detection. In this work, we introduce Global-Local Prompts (GalLoP), a new prompt learning method that learns multiple diverse prompts leveraging both global and local visual features. The training of the local prompts relies on local features with an enhanced vision-text alignment. To focus "},"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":"2407.01400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T15:50:15Z","cross_cats_sorted":[],"title_canon_sha256":"e74392d469485af4cc956859db1eb62f59326f0382aac92733fb8110cdd7eb06","abstract_canon_sha256":"ffab1bce29b9d45a4d2dc267b66137b6507e2ac945c84c490feb47cf9897c503"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:38.712601Z","signature_b64":"RqzQUfYqA9omB11lwkVqkUoBBDuYhCEgEx8pVeGt2/CR78OPf2G2zwn5SvAcvawbLPYzE1FQHob4rwvQtmKdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42bab98d6e31ce9323d8a3332f9af37a72c22e3a4efb3c3c207d13b85d79476e","last_reissued_at":"2026-07-05T09:41:38.712098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:38.712098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GalLoP: Learning Global and Local Prompts for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Elias Ramzi, Marc Lafon, Nicolas Audebert, Nicolas Thome","submitted_at":"2024-07-01T15:50:15Z","abstract_excerpt":"Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs), e.g. CLIP, for few-shot image classification. Despite their success, most prompt learning methods trade-off between classification accuracy and robustness, e.g. in domain generalization or out-of-distribution (OOD) detection. In this work, we introduce Global-Local Prompts (GalLoP), a new prompt learning method that learns multiple diverse prompts leveraging both global and local visual features. The training of the local prompts relies on local features with an enhanced vision-text alignment. To focus "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01400","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/2407.01400/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":"2407.01400","created_at":"2026-07-05T09:41:38.712162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01400v2","created_at":"2026-07-05T09:41:38.712162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01400","created_at":"2026-07-05T09:41:38.712162+00:00"},{"alias_kind":"pith_short_12","alias_value":"IK5LTDLOGHHJ","created_at":"2026-07-05T09:41:38.712162+00:00"},{"alias_kind":"pith_short_16","alias_value":"IK5LTDLOGHHJGI6Y","created_at":"2026-07-05T09:41:38.712162+00:00"},{"alias_kind":"pith_short_8","alias_value":"IK5LTDLO","created_at":"2026-07-05T09:41:38.712162+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/IK5LTDLOGHHJGI6YUMZS7GXTPJ","json":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ.json","graph_json":"https://pith.science/api/pith-number/IK5LTDLOGHHJGI6YUMZS7GXTPJ/graph.json","events_json":"https://pith.science/api/pith-number/IK5LTDLOGHHJGI6YUMZS7GXTPJ/events.json","paper":"https://pith.science/paper/IK5LTDLO"},"agent_actions":{"view_html":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ","download_json":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ.json","view_paper":"https://pith.science/paper/IK5LTDLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01400&json=true","fetch_graph":"https://pith.science/api/pith-number/IK5LTDLOGHHJGI6YUMZS7GXTPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IK5LTDLOGHHJGI6YUMZS7GXTPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ/action/storage_attestation","attest_author":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ/action/author_attestation","sign_citation":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ/action/citation_signature","submit_replication":"https://pith.science/pith/IK5LTDLOGHHJGI6YUMZS7GXTPJ/action/replication_record"}},"created_at":"2026-07-05T09:41:38.712162+00:00","updated_at":"2026-07-05T09:41:38.712162+00:00"}