{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LNLRSLFXMGLHQMI6TNG46FXCRD","short_pith_number":"pith:LNLRSLFX","schema_version":"1.0","canonical_sha256":"5b57192cb7619678311e9b4dcf16e288dc8ae68c8f226fa7987310003585a5c5","source":{"kind":"arxiv","id":"1707.07103","version":1},"attestation_state":"computed","paper":{"title":"PatchShuffle Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoliang Kang, Liang Zheng, Xuanyi Dong, Yi Yang","submitted_at":"2017-07-22T04:33:02Z","abstract_excerpt":"This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named ``PatchShuffle`` that can be adopted in any classification-oriented CNN models. It is easy to implement: in each mini-batch, images or feature maps are randomly chosen to undergo a transformation such that pixels within each local patch are shuffled. Through generating images and feature maps with interior orderless patches, PatchShuffle creates rich local variations, reduces the risk of network overfitting, and can be viewed as a beneficial supplement to va"},"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":"1707.07103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-22T04:33:02Z","cross_cats_sorted":[],"title_canon_sha256":"dad79ce2cc4a887c1343dc39982a3319e80ac9763c4d9b387add2c53264c8614","abstract_canon_sha256":"028f7a20ccce803918af99db94088cf529e55e4a627bd2a99d127a0682f3daca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:45.341891Z","signature_b64":"gy9Zn6X/k9ZBRRrzUm9Yap+qoPeEiszyfJOlgr41h+U4ThGwZRTvBEnHI7fQvVx2/QwmC4bvjCkeZ0zIiZByBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b57192cb7619678311e9b4dcf16e288dc8ae68c8f226fa7987310003585a5c5","last_reissued_at":"2026-05-18T00:39:45.341155Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:45.341155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchShuffle Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoliang Kang, Liang Zheng, Xuanyi Dong, Yi Yang","submitted_at":"2017-07-22T04:33:02Z","abstract_excerpt":"This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named ``PatchShuffle`` that can be adopted in any classification-oriented CNN models. It is easy to implement: in each mini-batch, images or feature maps are randomly chosen to undergo a transformation such that pixels within each local patch are shuffled. Through generating images and feature maps with interior orderless patches, PatchShuffle creates rich local variations, reduces the risk of network overfitting, and can be viewed as a beneficial supplement to va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07103","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":""},"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":"1707.07103","created_at":"2026-05-18T00:39:45.341271+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.07103v1","created_at":"2026-05-18T00:39:45.341271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07103","created_at":"2026-05-18T00:39:45.341271+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNLRSLFXMGLH","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNLRSLFXMGLHQMI6","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNLRSLFX","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20891","citing_title":"HDMoE: A Hierarchical Decoupling-Fusion Mixture-of-Experts Framework for Multimodal Cancer Survival Prediction","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD","json":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD.json","graph_json":"https://pith.science/api/pith-number/LNLRSLFXMGLHQMI6TNG46FXCRD/graph.json","events_json":"https://pith.science/api/pith-number/LNLRSLFXMGLHQMI6TNG46FXCRD/events.json","paper":"https://pith.science/paper/LNLRSLFX"},"agent_actions":{"view_html":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD","download_json":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD.json","view_paper":"https://pith.science/paper/LNLRSLFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.07103&json=true","fetch_graph":"https://pith.science/api/pith-number/LNLRSLFXMGLHQMI6TNG46FXCRD/graph.json","fetch_events":"https://pith.science/api/pith-number/LNLRSLFXMGLHQMI6TNG46FXCRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD/action/storage_attestation","attest_author":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD/action/author_attestation","sign_citation":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD/action/citation_signature","submit_replication":"https://pith.science/pith/LNLRSLFXMGLHQMI6TNG46FXCRD/action/replication_record"}},"created_at":"2026-05-18T00:39:45.341271+00:00","updated_at":"2026-05-18T00:39:45.341271+00:00"}