{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:S7ZW5DY6GNFRGMYKOI3AA3VEHS","short_pith_number":"pith:S7ZW5DY6","schema_version":"1.0","canonical_sha256":"97f36e8f1e334b13330a7236006ea43c956b1fba1c630cd988e8f1e62f01136f","source":{"kind":"arxiv","id":"1809.05375","version":2},"attestation_state":"computed","paper":{"title":"Style Augmentation: Data Augmentation via Style Randomization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Atapour-Abarghouei, Boguslaw Obara, Philip T. Jackson, Stephen Bonner, Toby Breckon","submitted_at":"2018-09-14T12:34:36Z","abstract_excerpt":"We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our style augmentation randomizes texture, contrast and color, while preserving shape and semantic content. This is accomplished by adapting an arbitrary style transfer network to perform style randomization, by sampling input style embeddings from a multivariate normal distribution instead of inferring them from a style image. In addition to standard classificat"},"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":"1809.05375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-14T12:34:36Z","cross_cats_sorted":[],"title_canon_sha256":"aee850c7cf9006e55ab1e3ee885fbe022e34567bce20eda7d3498b4bb214b575","abstract_canon_sha256":"9559675d64675082608cf04e15f7e423a9cb3d189da7d4f475234ecb227d1f34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:45.579762Z","signature_b64":"SjjNMPG0FBntGSJUsrnRGXkQoBJ8Dfi6R60MGDScDlELK6Jb7OF+nOMO6UGkXZ53mYXhkDK+GBGxWYO16m0ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97f36e8f1e334b13330a7236006ea43c956b1fba1c630cd988e8f1e62f01136f","last_reissued_at":"2026-05-17T23:48:45.579254Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:45.579254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style Augmentation: Data Augmentation via Style Randomization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Atapour-Abarghouei, Boguslaw Obara, Philip T. Jackson, Stephen Bonner, Toby Breckon","submitted_at":"2018-09-14T12:34:36Z","abstract_excerpt":"We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our style augmentation randomizes texture, contrast and color, while preserving shape and semantic content. This is accomplished by adapting an arbitrary style transfer network to perform style randomization, by sampling input style embeddings from a multivariate normal distribution instead of inferring them from a style image. In addition to standard classificat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05375","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":"1809.05375","created_at":"2026-05-17T23:48:45.579347+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.05375v2","created_at":"2026-05-17T23:48:45.579347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05375","created_at":"2026-05-17T23:48:45.579347+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7ZW5DY6GNFR","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7ZW5DY6GNFRGMYK","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7ZW5DY6","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05272","citing_title":"Introduction to Camera Pose Estimation with Deep Learning","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS","json":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS.json","graph_json":"https://pith.science/api/pith-number/S7ZW5DY6GNFRGMYKOI3AA3VEHS/graph.json","events_json":"https://pith.science/api/pith-number/S7ZW5DY6GNFRGMYKOI3AA3VEHS/events.json","paper":"https://pith.science/paper/S7ZW5DY6"},"agent_actions":{"view_html":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS","download_json":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS.json","view_paper":"https://pith.science/paper/S7ZW5DY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.05375&json=true","fetch_graph":"https://pith.science/api/pith-number/S7ZW5DY6GNFRGMYKOI3AA3VEHS/graph.json","fetch_events":"https://pith.science/api/pith-number/S7ZW5DY6GNFRGMYKOI3AA3VEHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS/action/storage_attestation","attest_author":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS/action/author_attestation","sign_citation":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS/action/citation_signature","submit_replication":"https://pith.science/pith/S7ZW5DY6GNFRGMYKOI3AA3VEHS/action/replication_record"}},"created_at":"2026-05-17T23:48:45.579347+00:00","updated_at":"2026-05-17T23:48:45.579347+00:00"}