{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KAHWL3FWBPPH37SDEOBRDEN35V","short_pith_number":"pith:KAHWL3FW","schema_version":"1.0","canonical_sha256":"500f65ecb60bde7dfe4323831191bbed61e3c3929dbf47beb3b85b72f00ba9cf","source":{"kind":"arxiv","id":"2105.05537","version":1},"attestation_state":"computed","paper":{"title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dongsheng Jiang, Hu Cao, Joy Chen, Manning Wang, Qi Tian, Xiaopeng Zhang, Yueyue Wang","submitted_at":"2021-05-12T09:30:26Z","abstract_excerpt":"In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis. Especially, the deep neural networks based on U-shaped architecture and skip-connections have been widely applied in a variety of medical image tasks. However, although CNN has achieved excellent performance, it cannot learn global and long-range semantic information interaction well due to the locality of the convolution operation. In this paper, we propose Swin-Unet, which is an Unet-like pure Transformer for medical image segmentation. The tokenized image patches are fed into the "},"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":"2105.05537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2021-05-12T09:30:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"32d6980f348bce1ac669c2bb5e6af6334ef7588100dafb9a1c915efe52111e60","abstract_canon_sha256":"f8ddf3a97e414a61341836f6896a9a271214d5af400ed3e48a983281b31cf0a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:52.098198Z","signature_b64":"/H91e3zbLPj1Oo6rW0q3coXuNj9ibGicrxwSv7mlaqfgHm/wEOjxraiHC1zz3E0GepHuBEGhM+I/6F5xxpWODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"500f65ecb60bde7dfe4323831191bbed61e3c3929dbf47beb3b85b72f00ba9cf","last_reissued_at":"2026-07-05T02:39:52.097794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:52.097794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dongsheng Jiang, Hu Cao, Joy Chen, Manning Wang, Qi Tian, Xiaopeng Zhang, Yueyue Wang","submitted_at":"2021-05-12T09:30:26Z","abstract_excerpt":"In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis. Especially, the deep neural networks based on U-shaped architecture and skip-connections have been widely applied in a variety of medical image tasks. However, although CNN has achieved excellent performance, it cannot learn global and long-range semantic information interaction well due to the locality of the convolution operation. In this paper, we propose Swin-Unet, which is an Unet-like pure Transformer for medical image segmentation. The tokenized image patches are fed into the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05537","kind":"arxiv","version":1},"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/2105.05537/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":"2105.05537","created_at":"2026-07-05T02:39:52.097850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05537v1","created_at":"2026-07-05T02:39:52.097850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05537","created_at":"2026-07-05T02:39:52.097850+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAHWL3FWBPPH","created_at":"2026-07-05T02:39:52.097850+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAHWL3FWBPPH37SD","created_at":"2026-07-05T02:39:52.097850+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAHWL3FW","created_at":"2026-07-05T02:39:52.097850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21414","citing_title":"2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07818","citing_title":"Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10931","citing_title":"Sparse Data Tree Canopy Segmentation: Fine-Tuning Leading Pretrained Models on Only 150 Images","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21465","citing_title":"ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19675","citing_title":"MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18148","citing_title":"Attention-ResUNet for Automated Fetal Head Segmentation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V","json":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V.json","graph_json":"https://pith.science/api/pith-number/KAHWL3FWBPPH37SDEOBRDEN35V/graph.json","events_json":"https://pith.science/api/pith-number/KAHWL3FWBPPH37SDEOBRDEN35V/events.json","paper":"https://pith.science/paper/KAHWL3FW"},"agent_actions":{"view_html":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V","download_json":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V.json","view_paper":"https://pith.science/paper/KAHWL3FW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05537&json=true","fetch_graph":"https://pith.science/api/pith-number/KAHWL3FWBPPH37SDEOBRDEN35V/graph.json","fetch_events":"https://pith.science/api/pith-number/KAHWL3FWBPPH37SDEOBRDEN35V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V/action/storage_attestation","attest_author":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V/action/author_attestation","sign_citation":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V/action/citation_signature","submit_replication":"https://pith.science/pith/KAHWL3FWBPPH37SDEOBRDEN35V/action/replication_record"}},"created_at":"2026-07-05T02:39:52.097850+00:00","updated_at":"2026-07-05T02:39:52.097850+00:00"}