{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4UT2CLU7TVK3DC4QIX5DPPSH7G","short_pith_number":"pith:4UT2CLU7","schema_version":"1.0","canonical_sha256":"e527a12e9f9d55b18b9045fa37be47f997250dd0aa64df0c3e5c7e4606b1c17e","source":{"kind":"arxiv","id":"1806.10779","version":5},"attestation_state":"computed","paper":{"title":"Differentiable Learning-to-Normalize via Switchable Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiamin Ren, Jingyu Li, Ping Luo, Ruimao Zhang, Zhanglin Peng","submitted_at":"2018-06-28T05:55:57Z","abstract_excerpt":"We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network. SN employs three distinct scopes to compute statistics (means and variances) including a channel, a layer, and a minibatch. SN switches between them by learning their importance weights in an end-to-end manner. It has several good properties. First, it adapts to various network architectures and tasks (see Fig.1). Second, it is robust to a wide range of batch sizes, maintaining high performance even when"},"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":"1806.10779","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-28T05:55:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"03b1c9ad440e593d845493cf278d8a96ff51364e6b0239ff0541e0b72e60fce7","abstract_canon_sha256":"9771ee8d6d8c8abb0ed5bd5b8b4af2b1afdeab37782cb339d4524192604f3f59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:53.906323Z","signature_b64":"YFqafFuUqo5WwnSzeuqggxN2QRK8i3Ls3q5zM0rV62AZmcEj9vkzJjbRErxSVhzycfcRUNIbM5HgUdvNSMVfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e527a12e9f9d55b18b9045fa37be47f997250dd0aa64df0c3e5c7e4606b1c17e","last_reissued_at":"2026-05-17T23:47:53.905828Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:53.905828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Learning-to-Normalize via Switchable Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiamin Ren, Jingyu Li, Ping Luo, Ruimao Zhang, Zhanglin Peng","submitted_at":"2018-06-28T05:55:57Z","abstract_excerpt":"We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network. SN employs three distinct scopes to compute statistics (means and variances) including a channel, a layer, and a minibatch. SN switches between them by learning their importance weights in an end-to-end manner. It has several good properties. First, it adapts to various network architectures and tasks (see Fig.1). Second, it is robust to a wide range of batch sizes, maintaining high performance even when"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.10779","kind":"arxiv","version":5},"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":"1806.10779","created_at":"2026-05-17T23:47:53.905912+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.10779v5","created_at":"2026-05-17T23:47:53.905912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.10779","created_at":"2026-05-17T23:47:53.905912+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UT2CLU7TVK3","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UT2CLU7TVK3DC4Q","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UT2CLU7","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2002.09053","citing_title":"Adapted Center and Scale Prediction: More Stable and More Accurate","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G","json":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G.json","graph_json":"https://pith.science/api/pith-number/4UT2CLU7TVK3DC4QIX5DPPSH7G/graph.json","events_json":"https://pith.science/api/pith-number/4UT2CLU7TVK3DC4QIX5DPPSH7G/events.json","paper":"https://pith.science/paper/4UT2CLU7"},"agent_actions":{"view_html":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G","download_json":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G.json","view_paper":"https://pith.science/paper/4UT2CLU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.10779&json=true","fetch_graph":"https://pith.science/api/pith-number/4UT2CLU7TVK3DC4QIX5DPPSH7G/graph.json","fetch_events":"https://pith.science/api/pith-number/4UT2CLU7TVK3DC4QIX5DPPSH7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G/action/storage_attestation","attest_author":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G/action/author_attestation","sign_citation":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G/action/citation_signature","submit_replication":"https://pith.science/pith/4UT2CLU7TVK3DC4QIX5DPPSH7G/action/replication_record"}},"created_at":"2026-05-17T23:47:53.905912+00:00","updated_at":"2026-05-17T23:47:53.905912+00:00"}