{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z2D2QS466SAR35RY3TORTAVJBF","short_pith_number":"pith:Z2D2QS46","schema_version":"1.0","canonical_sha256":"ce87a84b9ef4811df638dcdd1982a9094184e435a72720b729b343a2d3aac3ff","source":{"kind":"arxiv","id":"2205.08534","version":4},"attestation_state":"computed","paper":{"title":"Vision Transformer Adapter for Dense Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Junjun He, Tong Lu, Wenhai Wang, Yuchen Duan, Yu Qiao, Zhe Chen","submitted_at":"2022-05-17T17:59:11Z","abstract_excerpt":"This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers inferior performance on dense predictions due to weak prior assumptions. To address this issue, we propose the ViT-Adapter, which allows plain ViT to achieve comparable performance to vision-specific transformers. Specifically, the backbone in our framework is a plain ViT that can learn powerful representations from large-scale multi-modal data. When transferri"},"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":"2205.08534","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T17:59:11Z","cross_cats_sorted":[],"title_canon_sha256":"e21b6d618e770b7ee03e8fe716c0c541e374e521668b8d3d434a56dcee787510","abstract_canon_sha256":"5f8f89dc4daef52574d762ef4d64fbac63f2317bbe2199f6295b7714721031f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:45.988252Z","signature_b64":"25iJ9Qwapg3S182pVNyV8OiCRWFszG9sNjbw8x93gE8HkBMmNOE2XPlZPb67NDulML9OhUF/IPqWoEEgeKK5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce87a84b9ef4811df638dcdd1982a9094184e435a72720b729b343a2d3aac3ff","last_reissued_at":"2026-07-05T05:40:45.987856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:45.987856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Transformer Adapter for Dense Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Junjun He, Tong Lu, Wenhai Wang, Yuchen Duan, Yu Qiao, Zhe Chen","submitted_at":"2022-05-17T17:59:11Z","abstract_excerpt":"This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers inferior performance on dense predictions due to weak prior assumptions. To address this issue, we propose the ViT-Adapter, which allows plain ViT to achieve comparable performance to vision-specific transformers. Specifically, the backbone in our framework is a plain ViT that can learn powerful representations from large-scale multi-modal data. When transferri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08534","kind":"arxiv","version":4},"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/2205.08534/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":"2205.08534","created_at":"2026-07-05T05:40:45.987913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.08534v4","created_at":"2026-07-05T05:40:45.987913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08534","created_at":"2026-07-05T05:40:45.987913+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2D2QS466SAR","created_at":"2026-07-05T05:40:45.987913+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2D2QS466SAR35RY","created_at":"2026-07-05T05:40:45.987913+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2D2QS46","created_at":"2026-07-05T05:40:45.987913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25329","citing_title":"State Space Models Meet Remote Sensing: A Survey","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20971","citing_title":"UNITY: Attention Flow Networks for Adaptive Conditioning in Diffusion","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19944","citing_title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12218","citing_title":"Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21502","citing_title":"VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2301.01201","citing_title":"Uncertainty in Real-Time Semantic Segmentation on Embedded Systems","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17182","citing_title":"Radar-Guided Polynomial Fitting for Metric Depth Estimation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17748","citing_title":"Unleashing Vision Transformer Potential In Image Quality Assessment via Global-Local Adaptive Interaction","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19340","citing_title":"Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13417","citing_title":"Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2302.08453","citing_title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13780","citing_title":"Foundation Model-Driven Semantic Change Detection in Remote Sensing Imagery","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08276","citing_title":"Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21502","citing_title":"VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09088","citing_title":"Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09063","citing_title":"Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04058","citing_title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08074","citing_title":"DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF","json":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF.json","graph_json":"https://pith.science/api/pith-number/Z2D2QS466SAR35RY3TORTAVJBF/graph.json","events_json":"https://pith.science/api/pith-number/Z2D2QS466SAR35RY3TORTAVJBF/events.json","paper":"https://pith.science/paper/Z2D2QS46"},"agent_actions":{"view_html":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF","download_json":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF.json","view_paper":"https://pith.science/paper/Z2D2QS46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.08534&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2D2QS466SAR35RY3TORTAVJBF/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2D2QS466SAR35RY3TORTAVJBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF/action/storage_attestation","attest_author":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF/action/author_attestation","sign_citation":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF/action/citation_signature","submit_replication":"https://pith.science/pith/Z2D2QS466SAR35RY3TORTAVJBF/action/replication_record"}},"created_at":"2026-07-05T05:40:45.987913+00:00","updated_at":"2026-07-05T05:40:45.987913+00:00"}