{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ONR6ZCJFTHMC37WASNDX6QYMEJ","short_pith_number":"pith:ONR6ZCJF","schema_version":"1.0","canonical_sha256":"7363ec892599d82dfec093477f430c224bf6d3f3771e42b7d44bc8ff9e9495d0","source":{"kind":"arxiv","id":"2506.10575","version":1},"attestation_state":"computed","paper":{"title":"Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Kai Yu, Rick Siow Mong Goh, Salman Khan, Wangmeng Zuo, Xinxing Xu, Yong Liu","submitted_at":"2025-06-12T11:09:49Z","abstract_excerpt":"Benefited from image-text contrastive learning, pre-trained vision-language models, e.g., CLIP, allow to direct leverage texts as images (TaI) for parameter-efficient fine-tuning (PEFT). While CLIP is capable of making image features to be similar to the corresponding text features, the modality gap remains a nontrivial issue and limits image recognition performance of TaI. Using multi-label image recognition (MLR) as an example, we present a novel method, called T2I-PAL to tackle the modality gap issue when using only text captions for PEFT. The core design of T2I-PAL is to leverage pre-train"},"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":"2506.10575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-12T11:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"b72394049d5c5efb7e4183dba8692f8c5c36d4754c4f939e8d5a7161d682a1c5","abstract_canon_sha256":"a160b583fd31f1b52898252e704d65d9950f89632f0696912488dbcbcf68fe74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:26.583541Z","signature_b64":"053M+tHSIx3Kiultgfhbe7laUtlYNfFXb6O9MTGJufmP8+Bx0horO+8sOcIeTTcUMRIkfn8bF3MEvL84MUlvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7363ec892599d82dfec093477f430c224bf6d3f3771e42b7d44bc8ff9e9495d0","last_reissued_at":"2026-07-05T11:20:26.583006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:26.583006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Kai Yu, Rick Siow Mong Goh, Salman Khan, Wangmeng Zuo, Xinxing Xu, Yong Liu","submitted_at":"2025-06-12T11:09:49Z","abstract_excerpt":"Benefited from image-text contrastive learning, pre-trained vision-language models, e.g., CLIP, allow to direct leverage texts as images (TaI) for parameter-efficient fine-tuning (PEFT). While CLIP is capable of making image features to be similar to the corresponding text features, the modality gap remains a nontrivial issue and limits image recognition performance of TaI. Using multi-label image recognition (MLR) as an example, we present a novel method, called T2I-PAL to tackle the modality gap issue when using only text captions for PEFT. The core design of T2I-PAL is to leverage pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10575","kind":"arxiv","version":1},"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/2506.10575/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":"2506.10575","created_at":"2026-07-05T11:20:26.583067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10575v1","created_at":"2026-07-05T11:20:26.583067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10575","created_at":"2026-07-05T11:20:26.583067+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONR6ZCJFTHMC","created_at":"2026-07-05T11:20:26.583067+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONR6ZCJFTHMC37WA","created_at":"2026-07-05T11:20:26.583067+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONR6ZCJF","created_at":"2026-07-05T11:20:26.583067+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/ONR6ZCJFTHMC37WASNDX6QYMEJ","json":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ.json","graph_json":"https://pith.science/api/pith-number/ONR6ZCJFTHMC37WASNDX6QYMEJ/graph.json","events_json":"https://pith.science/api/pith-number/ONR6ZCJFTHMC37WASNDX6QYMEJ/events.json","paper":"https://pith.science/paper/ONR6ZCJF"},"agent_actions":{"view_html":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ","download_json":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ.json","view_paper":"https://pith.science/paper/ONR6ZCJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10575&json=true","fetch_graph":"https://pith.science/api/pith-number/ONR6ZCJFTHMC37WASNDX6QYMEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ONR6ZCJFTHMC37WASNDX6QYMEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ/action/storage_attestation","attest_author":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ/action/author_attestation","sign_citation":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ/action/citation_signature","submit_replication":"https://pith.science/pith/ONR6ZCJFTHMC37WASNDX6QYMEJ/action/replication_record"}},"created_at":"2026-07-05T11:20:26.583067+00:00","updated_at":"2026-07-05T11:20:26.583067+00:00"}