{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3WPPMWZ26AYS2D3XTXBLSXTPSA","short_pith_number":"pith:3WPPMWZ2","schema_version":"1.0","canonical_sha256":"dd9ef65b3af0312d0f779dc2b95e6f9001190a63f9a038cf96c629c150de0bd8","source":{"kind":"arxiv","id":"2203.16329","version":3},"attestation_state":"computed","paper":{"title":"Parameter-efficient Model Adaptation for Vision Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Xin Eric Wang, Xuehai He","submitted_at":"2022-03-29T05:30:09Z","abstract_excerpt":"In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either update all model parameters or leverage linear probes. In this paper, we aim to study parameter-efficient model adaptation strategies for vision transformers on the image classification task. We formulate efficient model adaptation as a subspace training problem and perform a comprehensive benchmarking over different efficient adaptation methods. We conduct an empirical study on e"},"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":"2203.16329","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T05:30:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c1dfbc13097cfb027bf8474a3ee45debdd962dcefd5cbecf88ad3794fbda9bb","abstract_canon_sha256":"a5fc1c8784e7ae415611249506245714a5035ca432d1ae7a04113a73680fcfce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:57.148112Z","signature_b64":"uqQBKgSAh5RZbv7m/iU7jVzCBWvvUv2yPdC1YtrnmZQfzeM3B1yR75OEg0Du18IMsv3siYLbDnsX7ioJp76uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd9ef65b3af0312d0f779dc2b95e6f9001190a63f9a038cf96c629c150de0bd8","last_reissued_at":"2026-07-05T06:30:57.147640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:57.147640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-efficient Model Adaptation for Vision Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Xin Eric Wang, Xuehai He","submitted_at":"2022-03-29T05:30:09Z","abstract_excerpt":"In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either update all model parameters or leverage linear probes. In this paper, we aim to study parameter-efficient model adaptation strategies for vision transformers on the image classification task. We formulate efficient model adaptation as a subspace training problem and perform a comprehensive benchmarking over different efficient adaptation methods. We conduct an empirical study on e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16329","kind":"arxiv","version":3},"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/2203.16329/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":"2203.16329","created_at":"2026-07-05T06:30:57.147704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16329v3","created_at":"2026-07-05T06:30:57.147704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16329","created_at":"2026-07-05T06:30:57.147704+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WPPMWZ26AYS","created_at":"2026-07-05T06:30:57.147704+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WPPMWZ26AYS2D3X","created_at":"2026-07-05T06:30:57.147704+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WPPMWZ2","created_at":"2026-07-05T06:30:57.147704+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/3WPPMWZ26AYS2D3XTXBLSXTPSA","json":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA.json","graph_json":"https://pith.science/api/pith-number/3WPPMWZ26AYS2D3XTXBLSXTPSA/graph.json","events_json":"https://pith.science/api/pith-number/3WPPMWZ26AYS2D3XTXBLSXTPSA/events.json","paper":"https://pith.science/paper/3WPPMWZ2"},"agent_actions":{"view_html":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA","download_json":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA.json","view_paper":"https://pith.science/paper/3WPPMWZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16329&json=true","fetch_graph":"https://pith.science/api/pith-number/3WPPMWZ26AYS2D3XTXBLSXTPSA/graph.json","fetch_events":"https://pith.science/api/pith-number/3WPPMWZ26AYS2D3XTXBLSXTPSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA/action/storage_attestation","attest_author":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA/action/author_attestation","sign_citation":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA/action/citation_signature","submit_replication":"https://pith.science/pith/3WPPMWZ26AYS2D3XTXBLSXTPSA/action/replication_record"}},"created_at":"2026-07-05T06:30:57.147704+00:00","updated_at":"2026-07-05T06:30:57.147704+00:00"}