{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GYHCD5LKR2SBTIH55FLF5PCZTY","short_pith_number":"pith:GYHCD5LK","schema_version":"1.0","canonical_sha256":"360e21f56a8ea419a0fde9565ebc599e1aa1b16aeabb96001b5fe5c67e83938c","source":{"kind":"arxiv","id":"2011.12672","version":3},"attestation_state":"computed","paper":{"title":"Batch Normalization Embeddings for Deep Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alessio Tonioni, Federico Tombari, Mattia Segu","submitted_at":"2020-11-25T12:02:57Z","abstract_excerpt":"Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize to unseen domains. Instead, first we explicitly train domain-dependant representations by using ad-hoc batch normalization layers to collect independent domain's statistics. Then, we propose to use these statistics to map domains in a shared latent space, where membership to a domain can be measured by means of a distance function. At test time, we project s"},"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":"2011.12672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-25T12:02:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"29762024bfba16772769eb56c5193807affa8810779fbb9df2d7c8401c5835ca","abstract_canon_sha256":"d88eeab507a69669ec3bd669c270d11a608d7e5078a6d012b5f84551e3137a0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:08.843138Z","signature_b64":"/5DVBPci87nWIB2oHMLPUwjrNEIRF9eP2rYjaIm0Ymo1mesPfkr/LyGC1OTop+eT1GD3kTLdpyv5Z87h1nIWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360e21f56a8ea419a0fde9565ebc599e1aa1b16aeabb96001b5fe5c67e83938c","last_reissued_at":"2026-07-05T02:41:08.842653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:08.842653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Batch Normalization Embeddings for Deep Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alessio Tonioni, Federico Tombari, Mattia Segu","submitted_at":"2020-11-25T12:02:57Z","abstract_excerpt":"Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize to unseen domains. Instead, first we explicitly train domain-dependant representations by using ad-hoc batch normalization layers to collect independent domain's statistics. Then, we propose to use these statistics to map domains in a shared latent space, where membership to a domain can be measured by means of a distance function. At test time, we project s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12672","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.12672/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":"2011.12672","created_at":"2026-07-05T02:41:08.842714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.12672v3","created_at":"2026-07-05T02:41:08.842714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12672","created_at":"2026-07-05T02:41:08.842714+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYHCD5LKR2SB","created_at":"2026-07-05T02:41:08.842714+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYHCD5LKR2SBTIH5","created_at":"2026-07-05T02:41:08.842714+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYHCD5LK","created_at":"2026-07-05T02:41:08.842714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15576","citing_title":"MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY","json":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY.json","graph_json":"https://pith.science/api/pith-number/GYHCD5LKR2SBTIH55FLF5PCZTY/graph.json","events_json":"https://pith.science/api/pith-number/GYHCD5LKR2SBTIH55FLF5PCZTY/events.json","paper":"https://pith.science/paper/GYHCD5LK"},"agent_actions":{"view_html":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY","download_json":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY.json","view_paper":"https://pith.science/paper/GYHCD5LK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.12672&json=true","fetch_graph":"https://pith.science/api/pith-number/GYHCD5LKR2SBTIH55FLF5PCZTY/graph.json","fetch_events":"https://pith.science/api/pith-number/GYHCD5LKR2SBTIH55FLF5PCZTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY/action/storage_attestation","attest_author":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY/action/author_attestation","sign_citation":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY/action/citation_signature","submit_replication":"https://pith.science/pith/GYHCD5LKR2SBTIH55FLF5PCZTY/action/replication_record"}},"created_at":"2026-07-05T02:41:08.842714+00:00","updated_at":"2026-07-05T02:41:08.842714+00:00"}