{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SIS7PJ2OBNRER5VDWW7APUIZNE","short_pith_number":"pith:SIS7PJ2O","schema_version":"1.0","canonical_sha256":"9225f7a74e0b6248f6a3b5be07d119693cab369287e17277e42694b38422fc29","source":{"kind":"arxiv","id":"2103.14899","version":2},"attestation_state":"computed","paper":{"title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Fu Chen, Quanfu Fan, Rameswar Panda","submitted_at":"2021-03-27T13:03:17Z","abstract_excerpt":"The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in transformer models for image classification. To this end, we propose a dual-branch transformer to combine image patches (i.e., tokens in a transformer) of different sizes to produce stronger image features. Our approach processes small-patch and large-patch tokens with two separate branches of different computational complexity and these tokens are then fuse"},"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":"2103.14899","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-27T13:03:17Z","cross_cats_sorted":[],"title_canon_sha256":"954b82cb6fbecfeaa1f926623738eca6928c7738df2e614e0e8baefe022c8357","abstract_canon_sha256":"7e2ad6d08c78e1245d927d309bd4502c7844a603900586bb0dd83d44c7525ef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:47.859261Z","signature_b64":"GXfR/hxfsugAf1EBXQ3R2zbsa3k1YdWoV/hvdfBua4mk/6Ab8ykdWtILchojf/25YRAJDXhiajsbFVdfDAgDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9225f7a74e0b6248f6a3b5be07d119693cab369287e17277e42694b38422fc29","last_reissued_at":"2026-07-05T03:07:47.858842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:47.858842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Fu Chen, Quanfu Fan, Rameswar Panda","submitted_at":"2021-03-27T13:03:17Z","abstract_excerpt":"The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in transformer models for image classification. To this end, we propose a dual-branch transformer to combine image patches (i.e., tokens in a transformer) of different sizes to produce stronger image features. Our approach processes small-patch and large-patch tokens with two separate branches of different computational complexity and these tokens are then fuse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14899","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/2103.14899/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":"2103.14899","created_at":"2026-07-05T03:07:47.858898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14899v2","created_at":"2026-07-05T03:07:47.858898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14899","created_at":"2026-07-05T03:07:47.858898+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIS7PJ2OBNRE","created_at":"2026-07-05T03:07:47.858898+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIS7PJ2OBNRER5VD","created_at":"2026-07-05T03:07:47.858898+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIS7PJ2O","created_at":"2026-07-05T03:07:47.858898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24790","citing_title":"Grad Detect: Gradient-Based Hallucination Detection in LLMs","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE","json":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE.json","graph_json":"https://pith.science/api/pith-number/SIS7PJ2OBNRER5VDWW7APUIZNE/graph.json","events_json":"https://pith.science/api/pith-number/SIS7PJ2OBNRER5VDWW7APUIZNE/events.json","paper":"https://pith.science/paper/SIS7PJ2O"},"agent_actions":{"view_html":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE","download_json":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE.json","view_paper":"https://pith.science/paper/SIS7PJ2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14899&json=true","fetch_graph":"https://pith.science/api/pith-number/SIS7PJ2OBNRER5VDWW7APUIZNE/graph.json","fetch_events":"https://pith.science/api/pith-number/SIS7PJ2OBNRER5VDWW7APUIZNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/action/storage_attestation","attest_author":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/action/author_attestation","sign_citation":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/action/citation_signature","submit_replication":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/action/replication_record"}},"created_at":"2026-07-05T03:07:47.858898+00:00","updated_at":"2026-07-05T03:07:47.858898+00:00"}