{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:URBXS5DMS4GNSBUZVF46OABKCR","short_pith_number":"pith:URBXS5DM","schema_version":"1.0","canonical_sha256":"a44379746c970cd90699a979e7002a14655e44ec648cd7bc009a379def65f664","source":{"kind":"arxiv","id":"2302.08106","version":2},"attestation_state":"computed","paper":{"title":"Towards Efficient Visual Adaption via Structural Re-parameterization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gen Luo, Guannan Jiang, Minglang Huang, Rongrong Ji, Xiaoshuai Sun, Yiyi Zhou, Zhiyu Wang","submitted_at":"2023-02-16T06:14:15Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) is an emerging research spot aimed at inexpensively adapting large-scale pre-trained models to downstream tasks. Recent advances have achieved great success in saving storage costs for various pre-trained models by updating a small number of parameters instead of full tuning. However, we notice that most existing PETL methods still incur non-negligible latency during inference. In this paper, we propose a parameter-efficient and computational friendly adapter for giant vision models, called RepAdapter. Specifically, we first prove that common adapta"},"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":"2302.08106","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-16T06:14:15Z","cross_cats_sorted":[],"title_canon_sha256":"681b03187338bd08f9e2b116624567010ea47cd1749c7380c9316321398de341","abstract_canon_sha256":"f941586f89cc9b593ac01e765d1657a5d3d21d9530bff3d41d29956f330556a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:14.301745Z","signature_b64":"1CifzcTO/sGlD+c79SqhDnYkZrr9ikz7wXGMESxqA93YqaUUAsEFXj5X72LNwyAy6m/V/ZHJtBrihjwHdAmKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a44379746c970cd90699a979e7002a14655e44ec648cd7bc009a379def65f664","last_reissued_at":"2026-07-05T05:53:14.301335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:14.301335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Efficient Visual Adaption via Structural Re-parameterization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gen Luo, Guannan Jiang, Minglang Huang, Rongrong Ji, Xiaoshuai Sun, Yiyi Zhou, Zhiyu Wang","submitted_at":"2023-02-16T06:14:15Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) is an emerging research spot aimed at inexpensively adapting large-scale pre-trained models to downstream tasks. Recent advances have achieved great success in saving storage costs for various pre-trained models by updating a small number of parameters instead of full tuning. However, we notice that most existing PETL methods still incur non-negligible latency during inference. In this paper, we propose a parameter-efficient and computational friendly adapter for giant vision models, called RepAdapter. Specifically, we first prove that common adapta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08106","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/2302.08106/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":"2302.08106","created_at":"2026-07-05T05:53:14.301395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.08106v2","created_at":"2026-07-05T05:53:14.301395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08106","created_at":"2026-07-05T05:53:14.301395+00:00"},{"alias_kind":"pith_short_12","alias_value":"URBXS5DMS4GN","created_at":"2026-07-05T05:53:14.301395+00:00"},{"alias_kind":"pith_short_16","alias_value":"URBXS5DMS4GNSBUZ","created_at":"2026-07-05T05:53:14.301395+00:00"},{"alias_kind":"pith_short_8","alias_value":"URBXS5DM","created_at":"2026-07-05T05:53:14.301395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22383","citing_title":"Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03837","citing_title":"Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28819","citing_title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05979","citing_title":"Prompt-Free and Efficient SAM2 Adaptation for Biomedical Semantic Segmentation via Dual Adapters","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06440","citing_title":"Visual prompting reimagined: The power of the Activation Prompts","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR","json":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR.json","graph_json":"https://pith.science/api/pith-number/URBXS5DMS4GNSBUZVF46OABKCR/graph.json","events_json":"https://pith.science/api/pith-number/URBXS5DMS4GNSBUZVF46OABKCR/events.json","paper":"https://pith.science/paper/URBXS5DM"},"agent_actions":{"view_html":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR","download_json":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR.json","view_paper":"https://pith.science/paper/URBXS5DM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.08106&json=true","fetch_graph":"https://pith.science/api/pith-number/URBXS5DMS4GNSBUZVF46OABKCR/graph.json","fetch_events":"https://pith.science/api/pith-number/URBXS5DMS4GNSBUZVF46OABKCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR/action/storage_attestation","attest_author":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR/action/author_attestation","sign_citation":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR/action/citation_signature","submit_replication":"https://pith.science/pith/URBXS5DMS4GNSBUZVF46OABKCR/action/replication_record"}},"created_at":"2026-07-05T05:53:14.301395+00:00","updated_at":"2026-07-05T05:53:14.301395+00:00"}