{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FDJ5PC2CJCENPZHPDPUS4OIWDR","short_pith_number":"pith:FDJ5PC2C","schema_version":"1.0","canonical_sha256":"28d3d78b424888d7e4ef1be92e39161c59c3d1a790ec28eb9aeffde57db8f630","source":{"kind":"arxiv","id":"1806.00420","version":2},"attestation_state":"computed","paper":{"title":"Whitening and Coloring batch transform for GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe","submitted_at":"2018-06-01T16:17:30Z","abstract_excerpt":"Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We show that our conditional Coloring can represent categorical conditioning information which largely helps the cGAN qualitative results. Moreover, we show that full-feature whitening is"},"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":"1806.00420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-01T16:17:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3459315d748920d913043cf6b1001cb0bc8cd7d51e9ce1592b7619d60a4efe38","abstract_canon_sha256":"1a25e8e0c7ed5238314e595d487f714f2ccbc28822c46e839aa548db117a0b75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:41.854010Z","signature_b64":"ua1VXVpAIR+Yl0DFWCOB6r7mRk8KKSrbTvRGllZ23hdh6k+jwzRy9KNgX6LQ62m5dxNbIZ3POoZ3juHN8pm8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d3d78b424888d7e4ef1be92e39161c59c3d1a790ec28eb9aeffde57db8f630","last_reissued_at":"2026-05-17T23:52:41.853338Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:41.853338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Whitening and Coloring batch transform for GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe","submitted_at":"2018-06-01T16:17:30Z","abstract_excerpt":"Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We show that our conditional Coloring can represent categorical conditioning information which largely helps the cGAN qualitative results. Moreover, we show that full-feature whitening is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00420","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":""},"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":"1806.00420","created_at":"2026-05-17T23:52:41.853438+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00420v2","created_at":"2026-05-17T23:52:41.853438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00420","created_at":"2026-05-17T23:52:41.853438+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDJ5PC2CJCEN","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDJ5PC2CJCENPZHP","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDJ5PC2C","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR","json":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR.json","graph_json":"https://pith.science/api/pith-number/FDJ5PC2CJCENPZHPDPUS4OIWDR/graph.json","events_json":"https://pith.science/api/pith-number/FDJ5PC2CJCENPZHPDPUS4OIWDR/events.json","paper":"https://pith.science/paper/FDJ5PC2C"},"agent_actions":{"view_html":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR","download_json":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR.json","view_paper":"https://pith.science/paper/FDJ5PC2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00420&json=true","fetch_graph":"https://pith.science/api/pith-number/FDJ5PC2CJCENPZHPDPUS4OIWDR/graph.json","fetch_events":"https://pith.science/api/pith-number/FDJ5PC2CJCENPZHPDPUS4OIWDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR/action/storage_attestation","attest_author":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR/action/author_attestation","sign_citation":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR/action/citation_signature","submit_replication":"https://pith.science/pith/FDJ5PC2CJCENPZHPDPUS4OIWDR/action/replication_record"}},"created_at":"2026-05-17T23:52:41.853438+00:00","updated_at":"2026-05-17T23:52:41.853438+00:00"}