{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OTE76YKFX7KTGPLILWZAB56SBM","short_pith_number":"pith:OTE76YKF","schema_version":"1.0","canonical_sha256":"74c9ff6145bfd5333d685db200f7d20b0851c8381f401d640e2a75b55ef9b56f","source":{"kind":"arxiv","id":"2311.15010","version":2},"attestation_state":"computed","paper":{"title":"Adapter is All You Need for Tuning Visual Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Dongshuo Yin, Leiyi Hu, Youqun Zhang","submitted_at":"2023-11-25T12:33:54Z","abstract_excerpt":"Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art fails to exceed the upper limit of full fine-tuning on challenging tasks like instance segmentation and semantic segmentation. To find a competitive alternative to full fine-tuning, we propose the Multi-cognitive Visual Adapter (Mona) tuning, a novel adapter-based tuning method. First, we introduce multiple vision-friendly filters into the adapter to enhance i"},"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":"2311.15010","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T12:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"a3be5b189c8118c3381b83ac1c0ca9dc1ddb6c5e4c814b7175d80bfe84a8142e","abstract_canon_sha256":"cab1df03a4a84ac15a938831a5d10fd961d06504d51355084a07ee6a4b7725a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:32.644717Z","signature_b64":"dR6uXd4LvzUXoYQ4v21jzPjcAtONLojf2AqvAXSRCd4HjJ3nH8/Yg4Lvbbs1k4GAu27PKR2IjWi3O+MuAiWaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74c9ff6145bfd5333d685db200f7d20b0851c8381f401d640e2a75b55ef9b56f","last_reissued_at":"2026-07-05T07:18:32.644248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:32.644248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapter is All You Need for Tuning Visual Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Dongshuo Yin, Leiyi Hu, Youqun Zhang","submitted_at":"2023-11-25T12:33:54Z","abstract_excerpt":"Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art fails to exceed the upper limit of full fine-tuning on challenging tasks like instance segmentation and semantic segmentation. To find a competitive alternative to full fine-tuning, we propose the Multi-cognitive Visual Adapter (Mona) tuning, a novel adapter-based tuning method. First, we introduce multiple vision-friendly filters into the adapter to enhance i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15010","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/2311.15010/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":"2311.15010","created_at":"2026-07-05T07:18:32.644304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15010v2","created_at":"2026-07-05T07:18:32.644304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15010","created_at":"2026-07-05T07:18:32.644304+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTE76YKFX7KT","created_at":"2026-07-05T07:18:32.644304+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTE76YKFX7KTGPLI","created_at":"2026-07-05T07:18:32.644304+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTE76YKF","created_at":"2026-07-05T07:18:32.644304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10130","citing_title":"Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17889","citing_title":"AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM","json":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM.json","graph_json":"https://pith.science/api/pith-number/OTE76YKFX7KTGPLILWZAB56SBM/graph.json","events_json":"https://pith.science/api/pith-number/OTE76YKFX7KTGPLILWZAB56SBM/events.json","paper":"https://pith.science/paper/OTE76YKF"},"agent_actions":{"view_html":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM","download_json":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM.json","view_paper":"https://pith.science/paper/OTE76YKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15010&json=true","fetch_graph":"https://pith.science/api/pith-number/OTE76YKFX7KTGPLILWZAB56SBM/graph.json","fetch_events":"https://pith.science/api/pith-number/OTE76YKFX7KTGPLILWZAB56SBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM/action/storage_attestation","attest_author":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM/action/author_attestation","sign_citation":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM/action/citation_signature","submit_replication":"https://pith.science/pith/OTE76YKFX7KTGPLILWZAB56SBM/action/replication_record"}},"created_at":"2026-07-05T07:18:32.644304+00:00","updated_at":"2026-07-05T07:18:32.644304+00:00"}