{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TYMXUFAWI62H6GQCU2VEML5SA5","short_pith_number":"pith:TYMXUFAW","schema_version":"1.0","canonical_sha256":"9e197a141647b47f1a02a6aa462fb20750c371ca1327ee79d535b5e0e4edae85","source":{"kind":"arxiv","id":"2103.12171","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Feature Augmentation and Normalization for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jianfeng Wang, Jingjing Liu, Lijuan Wang, Tianlong Chen, Yu Cheng, Zhangyang Wang, Zhe Gan","submitted_at":"2021-03-22T20:36:34Z","abstract_excerpt":"Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings, instead of relying on computationally-expensive pixel-level perturbations. We propose Adversarial Feature Augmentation and Normalization (A-FAN), which (i) first augments visual recognition models with adversarial features that integrate flexible scales of perturbation strengths, (ii) then extracts adversarial featur"},"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":"2103.12171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-22T20:36:34Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"fb7b5e278ab5e984819b62798aa176e2d20846246ad8b59ce3f88ffd5921f98b","abstract_canon_sha256":"e2130cb2cd20fc3062be4ed2011ef734675033f1c48699a929409996a770b985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:43.385932Z","signature_b64":"F8wTM1/qX5RiEiSC4o3lzrHsCI85/goFatBJVcRVcd+fKX4PtnJHr9fNpycM0KqiTMHrgcd4Id7X6Ijn8XImBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e197a141647b47f1a02a6aa462fb20750c371ca1327ee79d535b5e0e4edae85","last_reissued_at":"2026-07-05T02:25:43.382570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:43.382570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Feature Augmentation and Normalization for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jianfeng Wang, Jingjing Liu, Lijuan Wang, Tianlong Chen, Yu Cheng, Zhangyang Wang, Zhe Gan","submitted_at":"2021-03-22T20:36:34Z","abstract_excerpt":"Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings, instead of relying on computationally-expensive pixel-level perturbations. We propose Adversarial Feature Augmentation and Normalization (A-FAN), which (i) first augments visual recognition models with adversarial features that integrate flexible scales of perturbation strengths, (ii) then extracts adversarial featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12171","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.12171/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2103.12171","created_at":"2026-07-05T02:25:43.385331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12171v1","created_at":"2026-07-05T02:25:43.385331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12171","created_at":"2026-07-05T02:25:43.385331+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYMXUFAWI62H","created_at":"2026-07-05T02:25:43.385331+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYMXUFAWI62H6GQC","created_at":"2026-07-05T02:25:43.385331+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYMXUFAW","created_at":"2026-07-05T02:25:43.385331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21353","citing_title":"Group Relative Augmentation for Data Efficient Action Detection","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5","json":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5.json","graph_json":"https://pith.science/api/pith-number/TYMXUFAWI62H6GQCU2VEML5SA5/graph.json","events_json":"https://pith.science/api/pith-number/TYMXUFAWI62H6GQCU2VEML5SA5/events.json","paper":"https://pith.science/paper/TYMXUFAW"},"agent_actions":{"view_html":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5","download_json":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5.json","view_paper":"https://pith.science/paper/TYMXUFAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12171&json=true","fetch_graph":"https://pith.science/api/pith-number/TYMXUFAWI62H6GQCU2VEML5SA5/graph.json","fetch_events":"https://pith.science/api/pith-number/TYMXUFAWI62H6GQCU2VEML5SA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5/action/storage_attestation","attest_author":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5/action/author_attestation","sign_citation":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5/action/citation_signature","submit_replication":"https://pith.science/pith/TYMXUFAWI62H6GQCU2VEML5SA5/action/replication_record"}},"created_at":"2026-07-05T02:25:43.385331+00:00","updated_at":"2026-07-05T02:25:43.385331+00:00"}