{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H2BNZF4WVCU35TL2V24AIHHWKV","short_pith_number":"pith:H2BNZF4W","schema_version":"1.0","canonical_sha256":"3e82dc9796a8a9becd7aaeb8041cf6554fa01f4a3189ea41fa7cb0a47487d832","source":{"kind":"arxiv","id":"2311.03774","version":2},"attestation_state":"computed","paper":{"title":"Meta-Adapter: An Online Few-shot Learner for Vision-Language Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng cheng, Hang Wang, Hongbin Sun, Lin Song, Ruoyi Xue, Ying Shan, Yixiao Ge","submitted_at":"2023-11-07T07:27:16Z","abstract_excerpt":"The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP typically require offline fine-tuning of the parameters on few-shot samples, resulting in longer inference time and the risk of over-fitting in certain domains. To tackle these challenges, we propose the Meta-Adapter, a lightweight residual-style adapter, to refine the CLIP features guided by the few-shot samples in an online manner. With a few training sampl"},"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":"2311.03774","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T07:27:16Z","cross_cats_sorted":[],"title_canon_sha256":"57b7db98ac8144cd1325ed7c25d2560fe651ad12e6875f7814c6ffb4b77ae291","abstract_canon_sha256":"a1c580dde68030be9562cebaf9f878a8e22df8eda5c0f7562466737a2a9b0c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:24.726275Z","signature_b64":"7tSCXMPwIryeDa7xGolQplfxcCChZF9jy5ijV11x4uX155zRZ6u4DdkbNTKdrASX+fhfag/6sq7Tb62tcQpgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e82dc9796a8a9becd7aaeb8041cf6554fa01f4a3189ea41fa7cb0a47487d832","last_reissued_at":"2026-07-05T07:32:24.725804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:24.725804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Adapter: An Online Few-shot Learner for Vision-Language Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng cheng, Hang Wang, Hongbin Sun, Lin Song, Ruoyi Xue, Ying Shan, Yixiao Ge","submitted_at":"2023-11-07T07:27:16Z","abstract_excerpt":"The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP typically require offline fine-tuning of the parameters on few-shot samples, resulting in longer inference time and the risk of over-fitting in certain domains. To tackle these challenges, we propose the Meta-Adapter, a lightweight residual-style adapter, to refine the CLIP features guided by the few-shot samples in an online manner. With a few training sampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03774","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/2311.03774/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":"2311.03774","created_at":"2026-07-05T07:32:24.725864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03774v2","created_at":"2026-07-05T07:32:24.725864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03774","created_at":"2026-07-05T07:32:24.725864+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2BNZF4WVCU3","created_at":"2026-07-05T07:32:24.725864+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2BNZF4WVCU35TL2","created_at":"2026-07-05T07:32:24.725864+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2BNZF4W","created_at":"2026-07-05T07:32:24.725864+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/H2BNZF4WVCU35TL2V24AIHHWKV","json":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV.json","graph_json":"https://pith.science/api/pith-number/H2BNZF4WVCU35TL2V24AIHHWKV/graph.json","events_json":"https://pith.science/api/pith-number/H2BNZF4WVCU35TL2V24AIHHWKV/events.json","paper":"https://pith.science/paper/H2BNZF4W"},"agent_actions":{"view_html":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV","download_json":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV.json","view_paper":"https://pith.science/paper/H2BNZF4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03774&json=true","fetch_graph":"https://pith.science/api/pith-number/H2BNZF4WVCU35TL2V24AIHHWKV/graph.json","fetch_events":"https://pith.science/api/pith-number/H2BNZF4WVCU35TL2V24AIHHWKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV/action/storage_attestation","attest_author":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV/action/author_attestation","sign_citation":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV/action/citation_signature","submit_replication":"https://pith.science/pith/H2BNZF4WVCU35TL2V24AIHHWKV/action/replication_record"}},"created_at":"2026-07-05T07:32:24.725864+00:00","updated_at":"2026-07-05T07:32:24.725864+00:00"}