{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5EVFIZ5X6AWXBQ44BUBTOY45VK","short_pith_number":"pith:5EVFIZ5X","schema_version":"1.0","canonical_sha256":"e92a5467b7f02d70c39c0d0337639daabee8ceef99fbdc204076eddd1a4ab109","source":{"kind":"arxiv","id":"1805.08000","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Noise Layer: Regularize Neural Network By Adding Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jinmian Ye, Kunming Li, Ping Wang, Zenglin Xu, Zhonghui You","submitted_at":"2018-05-21T11:50:59Z","abstract_excerpt":"In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL) and its efficient version called Class Adversarial Noise Layer (CANL), which are able to significantly improve CNN's generalization ability by adding carefully crafted noise into the intermediate layer activations. ANL and CANL can be easily implemented and integrated with most of the mainstream CNN-based models. We compared the effects of the different types of noise and visually demonstrate that our proposed adversarial noise instruct CNN models to learn to extract cleaner feature maps, which furth"},"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":"1805.08000","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T11:50:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"82534b18a50567feb293b36807943d1ae80873a46e25bccca7b38e15b0c4c41f","abstract_canon_sha256":"3b8a5f662e2fa15018eb9ba1fa86a86ae23346a2593c868e6b0f5aa29878fae2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:59.332889Z","signature_b64":"3EwpTyxuJULYk5CQTy62eUpxzaslobaTglboJt3ovFku+2d1ufu9FgVjcpzAWA++LcMx/fQaFzo1Jh50VmSfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e92a5467b7f02d70c39c0d0337639daabee8ceef99fbdc204076eddd1a4ab109","last_reissued_at":"2026-05-18T00:01:59.332388Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:59.332388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Noise Layer: Regularize Neural Network By Adding Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jinmian Ye, Kunming Li, Ping Wang, Zenglin Xu, Zhonghui You","submitted_at":"2018-05-21T11:50:59Z","abstract_excerpt":"In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL) and its efficient version called Class Adversarial Noise Layer (CANL), which are able to significantly improve CNN's generalization ability by adding carefully crafted noise into the intermediate layer activations. ANL and CANL can be easily implemented and integrated with most of the mainstream CNN-based models. We compared the effects of the different types of noise and visually demonstrate that our proposed adversarial noise instruct CNN models to learn to extract cleaner feature maps, which furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08000","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":"1805.08000","created_at":"2026-05-18T00:01:59.332485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08000v2","created_at":"2026-05-18T00:01:59.332485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08000","created_at":"2026-05-18T00:01:59.332485+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EVFIZ5X6AWX","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EVFIZ5X6AWXBQ44","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EVFIZ5X","created_at":"2026-05-18T12:32:08.215937+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/5EVFIZ5X6AWXBQ44BUBTOY45VK","json":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK.json","graph_json":"https://pith.science/api/pith-number/5EVFIZ5X6AWXBQ44BUBTOY45VK/graph.json","events_json":"https://pith.science/api/pith-number/5EVFIZ5X6AWXBQ44BUBTOY45VK/events.json","paper":"https://pith.science/paper/5EVFIZ5X"},"agent_actions":{"view_html":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK","download_json":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK.json","view_paper":"https://pith.science/paper/5EVFIZ5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08000&json=true","fetch_graph":"https://pith.science/api/pith-number/5EVFIZ5X6AWXBQ44BUBTOY45VK/graph.json","fetch_events":"https://pith.science/api/pith-number/5EVFIZ5X6AWXBQ44BUBTOY45VK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK/action/storage_attestation","attest_author":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK/action/author_attestation","sign_citation":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK/action/citation_signature","submit_replication":"https://pith.science/pith/5EVFIZ5X6AWXBQ44BUBTOY45VK/action/replication_record"}},"created_at":"2026-05-18T00:01:59.332485+00:00","updated_at":"2026-05-18T00:01:59.332485+00:00"}