{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:46PENNQQ3F2GRVCRD3EVCPOSJN","short_pith_number":"pith:46PENNQQ","schema_version":"1.0","canonical_sha256":"e79e46b610d97468d4511ec9513dd24b71fd3b04c4891cc556fe176c91f3a641","source":{"kind":"arxiv","id":"1711.10288","version":1},"attestation_state":"computed","paper":{"title":"Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jacopo Cavazza, Pietro Morerio, Vittorio Murino","submitted_at":"2017-11-28T13:39:10Z","abstract_excerpt":"In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains. We formally demonstrate this hypothesis and, aiming at achieving an optimal alignment in practical cases, we adopt a more principled strategy which, differently from the current Euclidean approaches, deploys alignment along geodesics. Our pipeline can be implemented by adding to the standard classification loss (on the labeled source domai"},"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":"1711.10288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-28T13:39:10Z","cross_cats_sorted":[],"title_canon_sha256":"61e1f91cfcad3c1c9eeaaef73e5a88cc390cdd804886fb8c4f3f99165991f9c6","abstract_canon_sha256":"2ebe85758ea69fc3c9b61e0bf338a3b1cf82c2f70f4c6420adde3f8e71404329"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:22.715903Z","signature_b64":"QjsU+r3OTIpyu3MnigALfye4YB192Hglndn518u9oOla6WkQxH9s4YamaDhvixiJG4X4VS18rxOgBBl3Fx1nCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e79e46b610d97468d4511ec9513dd24b71fd3b04c4891cc556fe176c91f3a641","last_reissued_at":"2026-05-18T00:29:22.715240Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:22.715240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jacopo Cavazza, Pietro Morerio, Vittorio Murino","submitted_at":"2017-11-28T13:39:10Z","abstract_excerpt":"In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains. We formally demonstrate this hypothesis and, aiming at achieving an optimal alignment in practical cases, we adopt a more principled strategy which, differently from the current Euclidean approaches, deploys alignment along geodesics. Our pipeline can be implemented by adding to the standard classification loss (on the labeled source domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10288","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":""},"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":"1711.10288","created_at":"2026-05-18T00:29:22.715331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10288v1","created_at":"2026-05-18T00:29:22.715331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10288","created_at":"2026-05-18T00:29:22.715331+00:00"},{"alias_kind":"pith_short_12","alias_value":"46PENNQQ3F2G","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"46PENNQQ3F2GRVCR","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"46PENNQQ","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2503.00450","citing_title":"Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2509.23183","citing_title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07356","citing_title":"UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN","json":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN.json","graph_json":"https://pith.science/api/pith-number/46PENNQQ3F2GRVCRD3EVCPOSJN/graph.json","events_json":"https://pith.science/api/pith-number/46PENNQQ3F2GRVCRD3EVCPOSJN/events.json","paper":"https://pith.science/paper/46PENNQQ"},"agent_actions":{"view_html":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN","download_json":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN.json","view_paper":"https://pith.science/paper/46PENNQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10288&json=true","fetch_graph":"https://pith.science/api/pith-number/46PENNQQ3F2GRVCRD3EVCPOSJN/graph.json","fetch_events":"https://pith.science/api/pith-number/46PENNQQ3F2GRVCRD3EVCPOSJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN/action/storage_attestation","attest_author":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN/action/author_attestation","sign_citation":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN/action/citation_signature","submit_replication":"https://pith.science/pith/46PENNQQ3F2GRVCRD3EVCPOSJN/action/replication_record"}},"created_at":"2026-05-18T00:29:22.715331+00:00","updated_at":"2026-05-18T00:29:22.715331+00:00"}