{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZZFMXHFDY6HHQI35W2YZZCTTEE","short_pith_number":"pith:ZZFMXHFD","schema_version":"1.0","canonical_sha256":"ce4acb9ca3c78e78237db6b19c8a7321104e0ae1131f70876fe228d138fc2060","source":{"kind":"arxiv","id":"1902.06550","version":3},"attestation_state":"computed","paper":{"title":"LocalNorm: Robust Image Classification through Dynamically Regularized Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bojian Yin, Henk Corporaal, H. Steven Scholte, Sander M. Bohte, Siebren Schaafsma","submitted_at":"2019-02-18T12:58:23Z","abstract_excerpt":"While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation. Here, we describe a variant of Batch Normalization, LocalNorm, that regularizes the normalization layer in the spirit of Dropout while dynamically adapting to the local image intensity and contrast at test-time. We show that the resulting deep neural networks are much more resistant to noise-induced image degradation, improving accuracy by up to three times, while achieving the same or slightly better accuracy on non"},"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":"1902.06550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-18T12:58:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"045302eb45284a76c1706457435da99e3ecd2bf5340cd2a9d483c27c56fdeb78","abstract_canon_sha256":"3668c73a01d06fb2a85af87e1dad5e9b683f1f5c7c5966c5f4e123a353be890b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:14.626521Z","signature_b64":"2QG7gykznzNkwrXdOTyX+kNlZOFYQeYEZ15BE5KCY/6iWM0dM44BnAwxlB1QxaVgUBakLAinqBOydmynvjK7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce4acb9ca3c78e78237db6b19c8a7321104e0ae1131f70876fe228d138fc2060","last_reissued_at":"2026-05-17T23:52:14.625863Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:14.625863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LocalNorm: Robust Image Classification through Dynamically Regularized Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bojian Yin, Henk Corporaal, H. Steven Scholte, Sander M. Bohte, Siebren Schaafsma","submitted_at":"2019-02-18T12:58:23Z","abstract_excerpt":"While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation. Here, we describe a variant of Batch Normalization, LocalNorm, that regularizes the normalization layer in the spirit of Dropout while dynamically adapting to the local image intensity and contrast at test-time. We show that the resulting deep neural networks are much more resistant to noise-induced image degradation, improving accuracy by up to three times, while achieving the same or slightly better accuracy on non"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06550","kind":"arxiv","version":3},"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":"1902.06550","created_at":"2026-05-17T23:52:14.625953+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.06550v3","created_at":"2026-05-17T23:52:14.625953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06550","created_at":"2026-05-17T23:52:14.625953+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZFMXHFDY6HH","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZFMXHFDY6HHQI35","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZFMXHFD","created_at":"2026-05-18T12:33:33.725879+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/ZZFMXHFDY6HHQI35W2YZZCTTEE","json":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE.json","graph_json":"https://pith.science/api/pith-number/ZZFMXHFDY6HHQI35W2YZZCTTEE/graph.json","events_json":"https://pith.science/api/pith-number/ZZFMXHFDY6HHQI35W2YZZCTTEE/events.json","paper":"https://pith.science/paper/ZZFMXHFD"},"agent_actions":{"view_html":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE","download_json":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE.json","view_paper":"https://pith.science/paper/ZZFMXHFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.06550&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZFMXHFDY6HHQI35W2YZZCTTEE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZFMXHFDY6HHQI35W2YZZCTTEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE/action/storage_attestation","attest_author":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE/action/author_attestation","sign_citation":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE/action/citation_signature","submit_replication":"https://pith.science/pith/ZZFMXHFDY6HHQI35W2YZZCTTEE/action/replication_record"}},"created_at":"2026-05-17T23:52:14.625953+00:00","updated_at":"2026-05-17T23:52:14.625953+00:00"}