{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MOAZCU7VR5URCTU33B4EAV4MYL","short_pith_number":"pith:MOAZCU7V","schema_version":"1.0","canonical_sha256":"63819153f58f69114e9bd87840578cc2fbffa32e9683ff8b0772456fcffefa30","source":{"kind":"arxiv","id":"2412.14640","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Brouwer, Gertjan Burghouts, Jan Erik van Woerden, Marco Zullich, Matias Valdenegro-Toro","submitted_at":"2024-12-19T08:51:01Z","abstract_excerpt":"Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive Language-Image Pre-Training (CLIP) model through adaptive prompt tuning, guided by real-time visual inputs. Unlike existing techniques such as Context Optimization (CoOp) and Visual Prompt Tuning (VPT), which are constrained by static prompts or visual token reliance, the proposed approach leverages a cross-attention mechanism to dynamically refine text prompts for the"},"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":"2412.14640","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T08:51:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"23e0e9f96dcd676383a82764458fecb35f8123248797e50ba943710f6fba5317","abstract_canon_sha256":"669132bb92159bef67662e37edb3c242909cd295dc59042122f2a750c7493c03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:57.402117Z","signature_b64":"OkYqx1SSyFTYGLr28BhS7YWMLeWZeeKtoo4e4UiRNSGmAC3xwKqsioDPmCYgFE/aS1hbm87/P52IGBPEDXRvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63819153f58f69114e9bd87840578cc2fbffa32e9683ff8b0772456fcffefa30","last_reissued_at":"2026-07-05T10:52:57.401650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:57.401650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Brouwer, Gertjan Burghouts, Jan Erik van Woerden, Marco Zullich, Matias Valdenegro-Toro","submitted_at":"2024-12-19T08:51:01Z","abstract_excerpt":"Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive Language-Image Pre-Training (CLIP) model through adaptive prompt tuning, guided by real-time visual inputs. Unlike existing techniques such as Context Optimization (CoOp) and Visual Prompt Tuning (VPT), which are constrained by static prompts or visual token reliance, the proposed approach leverages a cross-attention mechanism to dynamically refine text prompts for the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14640","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/2412.14640/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":"2412.14640","created_at":"2026-07-05T10:52:57.401711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14640v2","created_at":"2026-07-05T10:52:57.401711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14640","created_at":"2026-07-05T10:52:57.401711+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOAZCU7VR5UR","created_at":"2026-07-05T10:52:57.401711+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOAZCU7VR5URCTU3","created_at":"2026-07-05T10:52:57.401711+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOAZCU7V","created_at":"2026-07-05T10:52:57.401711+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/MOAZCU7VR5URCTU33B4EAV4MYL","json":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL.json","graph_json":"https://pith.science/api/pith-number/MOAZCU7VR5URCTU33B4EAV4MYL/graph.json","events_json":"https://pith.science/api/pith-number/MOAZCU7VR5URCTU33B4EAV4MYL/events.json","paper":"https://pith.science/paper/MOAZCU7V"},"agent_actions":{"view_html":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL","download_json":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL.json","view_paper":"https://pith.science/paper/MOAZCU7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14640&json=true","fetch_graph":"https://pith.science/api/pith-number/MOAZCU7VR5URCTU33B4EAV4MYL/graph.json","fetch_events":"https://pith.science/api/pith-number/MOAZCU7VR5URCTU33B4EAV4MYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL/action/storage_attestation","attest_author":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL/action/author_attestation","sign_citation":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL/action/citation_signature","submit_replication":"https://pith.science/pith/MOAZCU7VR5URCTU33B4EAV4MYL/action/replication_record"}},"created_at":"2026-07-05T10:52:57.401711+00:00","updated_at":"2026-07-05T10:52:57.401711+00:00"}