{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SYYHQQDXFOBSZHEBPDRTIGVVI3","short_pith_number":"pith:SYYHQQDX","schema_version":"1.0","canonical_sha256":"96307840772b832c9c8178e3341ab546f47774d5c5beefee6367d9683b4f2482","source":{"kind":"arxiv","id":"2111.01236","version":2},"attestation_state":"computed","paper":{"title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Z. Pan, Dilin Wang, Hyoukjun Kwon, Jiaqi Gu, Liangzhen Lai, Meng Li, Vikas Chandra, Wei Ye, Yu-hsin Chen","submitted_at":"2021-11-01T19:49:52Z","abstract_excerpt":"Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs. Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs. We balance the model performance and efficiency "},"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":"2111.01236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T19:49:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1aee61d908d2aa4aa28e9c56f67930157c6d240c206f90b6b0ebbdf95720d975","abstract_canon_sha256":"f40f724b8575e3803e8297b043269036ad155440563919749b3b568b4c337504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:08.398891Z","signature_b64":"j+aniwz7PKizlR0tXb+3HB+whkVPPJH5PJMvYT9n+SUWTWNu3WBr4T/yMLwqCyivc3H+Y5YU43Yy641J9l3sAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96307840772b832c9c8178e3341ab546f47774d5c5beefee6367d9683b4f2482","last_reissued_at":"2026-07-05T03:34:08.398361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:08.398361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Z. Pan, Dilin Wang, Hyoukjun Kwon, Jiaqi Gu, Liangzhen Lai, Meng Li, Vikas Chandra, Wei Ye, Yu-hsin Chen","submitted_at":"2021-11-01T19:49:52Z","abstract_excerpt":"Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs. Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs. We balance the model performance and efficiency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01236","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/2111.01236/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":"2111.01236","created_at":"2026-07-05T03:34:08.398429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.01236v2","created_at":"2026-07-05T03:34:08.398429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01236","created_at":"2026-07-05T03:34:08.398429+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYYHQQDXFOBS","created_at":"2026-07-05T03:34:08.398429+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYYHQQDXFOBSZHEB","created_at":"2026-07-05T03:34:08.398429+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYYHQQDX","created_at":"2026-07-05T03:34:08.398429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07783","citing_title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3","json":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3.json","graph_json":"https://pith.science/api/pith-number/SYYHQQDXFOBSZHEBPDRTIGVVI3/graph.json","events_json":"https://pith.science/api/pith-number/SYYHQQDXFOBSZHEBPDRTIGVVI3/events.json","paper":"https://pith.science/paper/SYYHQQDX"},"agent_actions":{"view_html":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3","download_json":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3.json","view_paper":"https://pith.science/paper/SYYHQQDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.01236&json=true","fetch_graph":"https://pith.science/api/pith-number/SYYHQQDXFOBSZHEBPDRTIGVVI3/graph.json","fetch_events":"https://pith.science/api/pith-number/SYYHQQDXFOBSZHEBPDRTIGVVI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3/action/storage_attestation","attest_author":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3/action/author_attestation","sign_citation":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3/action/citation_signature","submit_replication":"https://pith.science/pith/SYYHQQDXFOBSZHEBPDRTIGVVI3/action/replication_record"}},"created_at":"2026-07-05T03:34:08.398429+00:00","updated_at":"2026-07-05T03:34:08.398429+00:00"}