{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J6SYE7PQFCG6C5MK3IBLCCMK5U","short_pith_number":"pith:J6SYE7PQ","schema_version":"1.0","canonical_sha256":"4fa5827df0288de1758ada02b1098aed1270a7c5e042d8ec1050e99110183b7f","source":{"kind":"arxiv","id":"2102.12122","version":2},"attestation_state":"computed","paper":{"title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng-Ping Fan, Ding Liang, Enze Xie, Kaitao Song, Ling Shao, Ping Luo, Tong Lu, Wenhai Wang, Xiang Li","submitted_at":"2021-02-24T08:33:55Z","abstract_excerpt":"Although using convolutional neural networks (CNNs) as backbones achieves great successes in computer vision, this work investigates a simple backbone network useful for many dense prediction tasks without convolutions. Unlike the recently-proposed Transformer model (e.g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks. PVT has several merits compared to prior arts. (1) Different from ViT that typically has low-resolution outputs and high computation"},"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":"2102.12122","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-24T08:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"4509609987af1b98899325af95cd55d19602222ee099586a4ed2a5e9dde14fc1","abstract_canon_sha256":"0dd5346383e97e3b7b73ad6319caaf97f0062520f9af559cf0c17cb14aea991e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:01.181791Z","signature_b64":"QIdY201FTYi7/jACC+khkK5rGQ/ocXtoOG4Kbgxj1OHXjPTP2m1z+vpuegyVZhjNiHCBD2fHRXHIb6Zm4LJHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fa5827df0288de1758ada02b1098aed1270a7c5e042d8ec1050e99110183b7f","last_reissued_at":"2026-07-05T03:05:01.181332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:01.181332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng-Ping Fan, Ding Liang, Enze Xie, Kaitao Song, Ling Shao, Ping Luo, Tong Lu, Wenhai Wang, Xiang Li","submitted_at":"2021-02-24T08:33:55Z","abstract_excerpt":"Although using convolutional neural networks (CNNs) as backbones achieves great successes in computer vision, this work investigates a simple backbone network useful for many dense prediction tasks without convolutions. Unlike the recently-proposed Transformer model (e.g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks. PVT has several merits compared to prior arts. (1) Different from ViT that typically has low-resolution outputs and high computation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12122","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/2102.12122/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":"2102.12122","created_at":"2026-07-05T03:05:01.181393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.12122v2","created_at":"2026-07-05T03:05:01.181393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12122","created_at":"2026-07-05T03:05:01.181393+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6SYE7PQFCG6","created_at":"2026-07-05T03:05:01.181393+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6SYE7PQFCG6C5MK","created_at":"2026-07-05T03:05:01.181393+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6SYE7PQ","created_at":"2026-07-05T03:05:01.181393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20561","citing_title":"TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living","ref_index":198,"is_internal_anchor":false},{"citing_arxiv_id":"2408.12974","citing_title":"Accuracy Improvement of Cell Image Segmentation Using Feedback Former","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20732","citing_title":"Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2103.14030","citing_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12380","citing_title":"Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U","json":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U.json","graph_json":"https://pith.science/api/pith-number/J6SYE7PQFCG6C5MK3IBLCCMK5U/graph.json","events_json":"https://pith.science/api/pith-number/J6SYE7PQFCG6C5MK3IBLCCMK5U/events.json","paper":"https://pith.science/paper/J6SYE7PQ"},"agent_actions":{"view_html":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U","download_json":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U.json","view_paper":"https://pith.science/paper/J6SYE7PQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.12122&json=true","fetch_graph":"https://pith.science/api/pith-number/J6SYE7PQFCG6C5MK3IBLCCMK5U/graph.json","fetch_events":"https://pith.science/api/pith-number/J6SYE7PQFCG6C5MK3IBLCCMK5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U/action/storage_attestation","attest_author":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U/action/author_attestation","sign_citation":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U/action/citation_signature","submit_replication":"https://pith.science/pith/J6SYE7PQFCG6C5MK3IBLCCMK5U/action/replication_record"}},"created_at":"2026-07-05T03:05:01.181393+00:00","updated_at":"2026-07-05T03:05:01.181393+00:00"}