{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QHEIBGHPI47FZ5EKU75JCJLDIN","short_pith_number":"pith:QHEIBGHP","schema_version":"1.0","canonical_sha256":"81c88098ef473e5cf48aa7fa912563436d9581a12f9576b259b6796806741bf8","source":{"kind":"arxiv","id":"1707.09842","version":2},"attestation_state":"computed","paper":{"title":"Deep Domain Adaptation by Geodesic Distance Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Luc Van Gool, Wen Li, Yifei Wang","submitted_at":"2017-07-13T11:34:11Z","abstract_excerpt":"In this paper, we propose a new approach called Deep LogCORAL for unsupervised visual domain adaptation. Our work builds on the recently proposed Deep CORAL method, which proposed to train a convolutional neural network and simultaneously minimize the Euclidean distance of convariance matrices between the source and target domains. We propose to use the Riemannian distance, approximated by Log-Euclidean distance, to replace the naive Euclidean distance in Deep CORAL. We also consider first-order information, and minimize the distance of mean vectors between two domains. We build an end-to-end "},"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":"1707.09842","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-13T11:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"0f66d0a0ffe15135758d3af8d3e4cd327954ab4eb1025ef64a695d3b7864efcb","abstract_canon_sha256":"030d7970730a987514dce072f8a409a25f85b6fe23dd59a0146362d199f988f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:06.356326Z","signature_b64":"xnARy5MtX6fJH/5QEMbodyyTNoLRre6/DJL1Oz6MiC0iNZ3/nD+YtrmQh4oO8qbdE3ornY1PEN9voVq/V0GXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81c88098ef473e5cf48aa7fa912563436d9581a12f9576b259b6796806741bf8","last_reissued_at":"2026-05-18T00:33:06.355659Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:06.355659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Domain Adaptation by Geodesic Distance Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Luc Van Gool, Wen Li, Yifei Wang","submitted_at":"2017-07-13T11:34:11Z","abstract_excerpt":"In this paper, we propose a new approach called Deep LogCORAL for unsupervised visual domain adaptation. Our work builds on the recently proposed Deep CORAL method, which proposed to train a convolutional neural network and simultaneously minimize the Euclidean distance of convariance matrices between the source and target domains. We propose to use the Riemannian distance, approximated by Log-Euclidean distance, to replace the naive Euclidean distance in Deep CORAL. We also consider first-order information, and minimize the distance of mean vectors between two domains. We build an end-to-end "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09842","kind":"arxiv","version":2},"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":"1707.09842","created_at":"2026-05-18T00:33:06.355760+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09842v2","created_at":"2026-05-18T00:33:06.355760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09842","created_at":"2026-05-18T00:33:06.355760+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHEIBGHPI47F","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHEIBGHPI47FZ5EK","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHEIBGHP","created_at":"2026-05-18T12:31:37.085036+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/QHEIBGHPI47FZ5EKU75JCJLDIN","json":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN.json","graph_json":"https://pith.science/api/pith-number/QHEIBGHPI47FZ5EKU75JCJLDIN/graph.json","events_json":"https://pith.science/api/pith-number/QHEIBGHPI47FZ5EKU75JCJLDIN/events.json","paper":"https://pith.science/paper/QHEIBGHP"},"agent_actions":{"view_html":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN","download_json":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN.json","view_paper":"https://pith.science/paper/QHEIBGHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09842&json=true","fetch_graph":"https://pith.science/api/pith-number/QHEIBGHPI47FZ5EKU75JCJLDIN/graph.json","fetch_events":"https://pith.science/api/pith-number/QHEIBGHPI47FZ5EKU75JCJLDIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN/action/storage_attestation","attest_author":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN/action/author_attestation","sign_citation":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN/action/citation_signature","submit_replication":"https://pith.science/pith/QHEIBGHPI47FZ5EKU75JCJLDIN/action/replication_record"}},"created_at":"2026-05-18T00:33:06.355760+00:00","updated_at":"2026-05-18T00:33:06.355760+00:00"}