{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UUJSYGMKGQ2XMTZ33T5PB5WHOP","short_pith_number":"pith:UUJSYGMK","schema_version":"1.0","canonical_sha256":"a5132c198a3435764f3bdcfaf0f6c773ecbbb1ab4f4961200d5b923d4bde9588","source":{"kind":"arxiv","id":"2010.07810","version":1},"attestation_state":"computed","paper":{"title":"Does Data Augmentation Benefit from Split BatchNorms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amil Merchant, Barret Zoph, Ekin Dogus Cubuk","submitted_at":"2020-10-15T15:00:43Z","abstract_excerpt":"Data augmentation has emerged as a powerful technique for improving the performance of deep neural networks and led to state-of-the-art results in computer vision. However, state-of-the-art data augmentation strongly distorts training images, leading to a disparity between examples seen during training and inference. In this work, we explore a recently proposed training paradigm in order to correct for this disparity: using an auxiliary BatchNorm for the potentially out-of-distribution, strongly augmented images. Our experiments then focus on how to define the BatchNorm parameters that are use"},"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":"2010.07810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T15:00:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2791709576f0d50673292bd74dacf333be3664d9b59e8fcd1cbb1f30e4ed355e","abstract_canon_sha256":"5e54a97fc1c6856c15f00c79bf0372d8fc3ae17a6fa59f490a24fb64163bed85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:21.034026Z","signature_b64":"N/+BHSUypjcYgmjXpD0sZSkz07AAZ9IfSrLd7IDeu06fx2N4YMbJU6Gw4aPtI4M3E2fQewE/+run7dYvDxRMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5132c198a3435764f3bdcfaf0f6c773ecbbb1ab4f4961200d5b923d4bde9588","last_reissued_at":"2026-07-05T01:43:21.033664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:21.033664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Data Augmentation Benefit from Split BatchNorms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amil Merchant, Barret Zoph, Ekin Dogus Cubuk","submitted_at":"2020-10-15T15:00:43Z","abstract_excerpt":"Data augmentation has emerged as a powerful technique for improving the performance of deep neural networks and led to state-of-the-art results in computer vision. However, state-of-the-art data augmentation strongly distorts training images, leading to a disparity between examples seen during training and inference. In this work, we explore a recently proposed training paradigm in order to correct for this disparity: using an auxiliary BatchNorm for the potentially out-of-distribution, strongly augmented images. Our experiments then focus on how to define the BatchNorm parameters that are use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07810","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/2010.07810/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":"2010.07810","created_at":"2026-07-05T01:43:21.033729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07810v1","created_at":"2026-07-05T01:43:21.033729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07810","created_at":"2026-07-05T01:43:21.033729+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUJSYGMKGQ2X","created_at":"2026-07-05T01:43:21.033729+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUJSYGMKGQ2XMTZ3","created_at":"2026-07-05T01:43:21.033729+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUJSYGMK","created_at":"2026-07-05T01:43:21.033729+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/UUJSYGMKGQ2XMTZ33T5PB5WHOP","json":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP.json","graph_json":"https://pith.science/api/pith-number/UUJSYGMKGQ2XMTZ33T5PB5WHOP/graph.json","events_json":"https://pith.science/api/pith-number/UUJSYGMKGQ2XMTZ33T5PB5WHOP/events.json","paper":"https://pith.science/paper/UUJSYGMK"},"agent_actions":{"view_html":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP","download_json":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP.json","view_paper":"https://pith.science/paper/UUJSYGMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07810&json=true","fetch_graph":"https://pith.science/api/pith-number/UUJSYGMKGQ2XMTZ33T5PB5WHOP/graph.json","fetch_events":"https://pith.science/api/pith-number/UUJSYGMKGQ2XMTZ33T5PB5WHOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP/action/storage_attestation","attest_author":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP/action/author_attestation","sign_citation":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP/action/citation_signature","submit_replication":"https://pith.science/pith/UUJSYGMKGQ2XMTZ33T5PB5WHOP/action/replication_record"}},"created_at":"2026-07-05T01:43:21.033729+00:00","updated_at":"2026-07-05T01:43:21.033729+00:00"}