{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:OGTRUCDJVQBDOVQMKJSV6LE3BF","short_pith_number":"pith:OGTRUCDJ","schema_version":"1.0","canonical_sha256":"71a71a0869ac0237560c52655f2c9b0968f9504353f8b3e3e76fb6a6d1179f0e","source":{"kind":"arxiv","id":"1603.04779","version":4},"attestation_state":"computed","paper":{"title":"Revisiting Batch Normalization For Practical Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianping Shi, Jiaying Liu, Naiyan Wang, Xiaodi Hou, Yanghao Li","submitted_at":"2016-03-15T17:44:32Z","abstract_excerpt":"Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain. Recent study (Tommasi et al. 2015) shows that a DNN has strong dependency towards the training dataset, and the learned features cannot be easily transferred to a different but relevant task without fine-tuning. In this paper, we propose a simple yet powerful remedy, called A"},"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":"1603.04779","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-15T17:44:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f9cb2b4a2ff977c24c5f57c9f66302f35ad73ffeba11ddc3eb7e245a82732358","abstract_canon_sha256":"c6da8e5a6ab0a9661ccae69bef5f4f123f10208a444403cff85cab039fce6c7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:58.662706Z","signature_b64":"+RobFCPgvp5+dGkyLg19nQQwyJnzrnSKBYsz9rjKUWcFaRPfcgj4NEl+tsi9E7O/jbbV9mTpnMhb3XOrgkJaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71a71a0869ac0237560c52655f2c9b0968f9504353f8b3e3e76fb6a6d1179f0e","last_reissued_at":"2026-05-18T00:59:58.662247Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:58.662247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Batch Normalization For Practical Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianping Shi, Jiaying Liu, Naiyan Wang, Xiaodi Hou, Yanghao Li","submitted_at":"2016-03-15T17:44:32Z","abstract_excerpt":"Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain. Recent study (Tommasi et al. 2015) shows that a DNN has strong dependency towards the training dataset, and the learned features cannot be easily transferred to a different but relevant task without fine-tuning. In this paper, we propose a simple yet powerful remedy, called A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04779","kind":"arxiv","version":4},"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":"1603.04779","created_at":"2026-05-18T00:59:58.662320+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.04779v4","created_at":"2026-05-18T00:59:58.662320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04779","created_at":"2026-05-18T00:59:58.662320+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGTRUCDJVQBD","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGTRUCDJVQBDOVQM","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGTRUCDJ","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15452","citing_title":"DoSReMC: Domain Shift Resilient Mammography Classification using Batch Normalization Adaptation","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25435","citing_title":"PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11590","citing_title":"Learning Robustness at Test-Time from a Non-Robust Teacher","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13546","citing_title":"Learning Inference Concurrency in DynamicGate MLP Structural and Mathematical Justification","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF","json":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF.json","graph_json":"https://pith.science/api/pith-number/OGTRUCDJVQBDOVQMKJSV6LE3BF/graph.json","events_json":"https://pith.science/api/pith-number/OGTRUCDJVQBDOVQMKJSV6LE3BF/events.json","paper":"https://pith.science/paper/OGTRUCDJ"},"agent_actions":{"view_html":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF","download_json":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF.json","view_paper":"https://pith.science/paper/OGTRUCDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.04779&json=true","fetch_graph":"https://pith.science/api/pith-number/OGTRUCDJVQBDOVQMKJSV6LE3BF/graph.json","fetch_events":"https://pith.science/api/pith-number/OGTRUCDJVQBDOVQMKJSV6LE3BF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF/action/storage_attestation","attest_author":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF/action/author_attestation","sign_citation":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF/action/citation_signature","submit_replication":"https://pith.science/pith/OGTRUCDJVQBDOVQMKJSV6LE3BF/action/replication_record"}},"created_at":"2026-05-18T00:59:58.662320+00:00","updated_at":"2026-05-18T00:59:58.662320+00:00"}