{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SGIGU2WLOIA6NVSDLQY3TCP7MA","short_pith_number":"pith:SGIGU2WL","schema_version":"1.0","canonical_sha256":"91906a6acb7201e6d6435c31b989ff6023ea4b66e72858ebb0f135c0286a0665","source":{"kind":"arxiv","id":"2106.03650","version":1},"attestation_state":"computed","paper":{"title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Gang Yu, Guozhong Luo, Pei Cheng, Youcheng Ben, Zilong Huang","submitted_at":"2021-06-07T14:22:07Z","abstract_excerpt":"Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code."},"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":"2106.03650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T14:22:07Z","cross_cats_sorted":[],"title_canon_sha256":"cce61abf32dc0335029bc662210d3bc1938cb9b29eaca503c832c89f6e4ed8c1","abstract_canon_sha256":"4b9f5a5b6583ef3be69d504b48d526e05b26452cc6c45d3aac1899621d3f98b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:51.883380Z","signature_b64":"HxiAnMneVsUkQ2x1tQJO7wni2Y4yfQCIN6VOvHx/scbHDzh7E+c3jTyTQ6gqCZ6+FUeuGWHrPlIfn3GjCxB/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91906a6acb7201e6d6435c31b989ff6023ea4b66e72858ebb0f135c0286a0665","last_reissued_at":"2026-07-05T02:46:51.882900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:51.882900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Gang Yu, Guozhong Luo, Pei Cheng, Youcheng Ben, Zilong Huang","submitted_at":"2021-06-07T14:22:07Z","abstract_excerpt":"Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03650","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/2106.03650/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":"2106.03650","created_at":"2026-07-05T02:46:51.882959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03650v1","created_at":"2026-07-05T02:46:51.882959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03650","created_at":"2026-07-05T02:46:51.882959+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGIGU2WLOIA6","created_at":"2026-07-05T02:46:51.882959+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGIGU2WLOIA6NVSD","created_at":"2026-07-05T02:46:51.882959+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGIGU2WL","created_at":"2026-07-05T02:46:51.882959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06783","citing_title":"Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA","json":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA.json","graph_json":"https://pith.science/api/pith-number/SGIGU2WLOIA6NVSDLQY3TCP7MA/graph.json","events_json":"https://pith.science/api/pith-number/SGIGU2WLOIA6NVSDLQY3TCP7MA/events.json","paper":"https://pith.science/paper/SGIGU2WL"},"agent_actions":{"view_html":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA","download_json":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA.json","view_paper":"https://pith.science/paper/SGIGU2WL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03650&json=true","fetch_graph":"https://pith.science/api/pith-number/SGIGU2WLOIA6NVSDLQY3TCP7MA/graph.json","fetch_events":"https://pith.science/api/pith-number/SGIGU2WLOIA6NVSDLQY3TCP7MA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA/action/storage_attestation","attest_author":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA/action/author_attestation","sign_citation":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA/action/citation_signature","submit_replication":"https://pith.science/pith/SGIGU2WLOIA6NVSDLQY3TCP7MA/action/replication_record"}},"created_at":"2026-07-05T02:46:51.882959+00:00","updated_at":"2026-07-05T02:46:51.882959+00:00"}