{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NWKFONAMSCLMIJQB6YKL5S6THD","short_pith_number":"pith:NWKFONAM","schema_version":"1.0","canonical_sha256":"6d9457340c9096c42601f614becbd338e3d8c314903f30828a127b80eb47d094","source":{"kind":"arxiv","id":"2111.03930","version":2},"attestation_state":"computed","paper":{"title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jifeng Dai, Kunchang Li, Peng Gao, Renrui Zhang, Rongyao Fang, Wei Zhang, Yu Qiao","submitted_at":"2021-11-06T18:09:22Z","abstract_excerpt":"Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows impressive performance on zero-shot knowledge transfer to downstream tasks. To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification. However, such a process still needs extra training and computational resources. In this paper, we propose \\textbf{T}raining-Free CL\\textbf{IP}-\\textbf"},"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":"2111.03930","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-06T18:09:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"eef69d27be97e093d9a649ad7c98e6dba97e25203d8d2d767a732f4a5a03487d","abstract_canon_sha256":"1904dd367ca314021edca16bf0d9bb6b8bac1fbe4d6701e868f1b0568f665645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:32.179408Z","signature_b64":"iWYeaTQ9h4fEZI8Fibj3eZJYSpgJHlkvamMyBNAk4c8KXrCT9+m3TFPdk49luEJ4LCPs2h0MIB5UfVZc2r6/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d9457340c9096c42601f614becbd338e3d8c314903f30828a127b80eb47d094","last_reissued_at":"2026-07-05T03:31:32.178954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:32.178954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jifeng Dai, Kunchang Li, Peng Gao, Renrui Zhang, Rongyao Fang, Wei Zhang, Yu Qiao","submitted_at":"2021-11-06T18:09:22Z","abstract_excerpt":"Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows impressive performance on zero-shot knowledge transfer to downstream tasks. To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification. However, such a process still needs extra training and computational resources. In this paper, we propose \\textbf{T}raining-Free CL\\textbf{IP}-\\textbf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03930","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/2111.03930/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":"2111.03930","created_at":"2026-07-05T03:31:32.179014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03930v2","created_at":"2026-07-05T03:31:32.179014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03930","created_at":"2026-07-05T03:31:32.179014+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWKFONAMSCLM","created_at":"2026-07-05T03:31:32.179014+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWKFONAMSCLMIJQB","created_at":"2026-07-05T03:31:32.179014+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWKFONAM","created_at":"2026-07-05T03:31:32.179014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06309","citing_title":"Token-Based Dual-view Fusion and Adaptation of Large Vision Models for Breast Cancer Classification","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19944","citing_title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11682","citing_title":"Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04922","citing_title":"Geometry-Aware Distillation for Prompt Tuning Biomedical Vision-Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16335","citing_title":"On the Provable Importance of Gradients for Language-Assisted Image Clustering","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18158","citing_title":"Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03740","citing_title":"CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26036","citing_title":"SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22125","citing_title":"GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2302.05543","citing_title":"Adding Conditional Control to Text-to-Image Diffusion Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":260,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11659","citing_title":"Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08181","citing_title":"Text-Guided Multi-Scale Frequency Representation Adaptation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04504","citing_title":"SpecPL: Disentangling Spectral Granularity for Prompt Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05910","citing_title":"Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD","json":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD.json","graph_json":"https://pith.science/api/pith-number/NWKFONAMSCLMIJQB6YKL5S6THD/graph.json","events_json":"https://pith.science/api/pith-number/NWKFONAMSCLMIJQB6YKL5S6THD/events.json","paper":"https://pith.science/paper/NWKFONAM"},"agent_actions":{"view_html":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD","download_json":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD.json","view_paper":"https://pith.science/paper/NWKFONAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03930&json=true","fetch_graph":"https://pith.science/api/pith-number/NWKFONAMSCLMIJQB6YKL5S6THD/graph.json","fetch_events":"https://pith.science/api/pith-number/NWKFONAMSCLMIJQB6YKL5S6THD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD/action/storage_attestation","attest_author":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD/action/author_attestation","sign_citation":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD/action/citation_signature","submit_replication":"https://pith.science/pith/NWKFONAMSCLMIJQB6YKL5S6THD/action/replication_record"}},"created_at":"2026-07-05T03:31:32.179014+00:00","updated_at":"2026-07-05T03:31:32.179014+00:00"}