{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AAQTUMOEEZMVE7PE6NNBEXTIIW","short_pith_number":"pith:AAQTUMOE","schema_version":"1.0","canonical_sha256":"00213a31c42659527de4f35a125e6845ad1b93507bf3e64d4f5520b264dcaa26","source":{"kind":"arxiv","id":"1811.05042","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Local Feature Patterns for Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junsong Yuan, Jun Wen, Nenggan Zheng, Qian Zheng, Risheng Liu, Zhefeng Gong","submitted_at":"2018-11-12T23:23:23Z","abstract_excerpt":"Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local fe"},"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":"1811.05042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-12T23:23:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f8cc3d34522dcc06d0afb3150868c8f9267bfb140a15e2ac3d1ee85510e94d6b","abstract_canon_sha256":"72199a964f5dbc338a1c191b165507db6535fd971941ff3386cf16a89d1b0ea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.366597Z","signature_b64":"j6XLUkgRFbbGaD63PjdXeVEw01e81T+aa2WJA9lapEURnW5B0cqQTAXloktzX11m7hTg6C20baCvh5P66YVICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00213a31c42659527de4f35a125e6845ad1b93507bf3e64d4f5520b264dcaa26","last_reissued_at":"2026-05-18T00:00:29.365969Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.365969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Local Feature Patterns for Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junsong Yuan, Jun Wen, Nenggan Zheng, Qian Zheng, Risheng Liu, Zhefeng Gong","submitted_at":"2018-11-12T23:23:23Z","abstract_excerpt":"Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05042","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":"1811.05042","created_at":"2026-05-18T00:00:29.366051+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.05042v2","created_at":"2026-05-18T00:00:29.366051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05042","created_at":"2026-05-18T00:00:29.366051+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAQTUMOEEZMV","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAQTUMOEEZMVE7PE","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAQTUMOE","created_at":"2026-05-18T12:32:13.499390+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/AAQTUMOEEZMVE7PE6NNBEXTIIW","json":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW.json","graph_json":"https://pith.science/api/pith-number/AAQTUMOEEZMVE7PE6NNBEXTIIW/graph.json","events_json":"https://pith.science/api/pith-number/AAQTUMOEEZMVE7PE6NNBEXTIIW/events.json","paper":"https://pith.science/paper/AAQTUMOE"},"agent_actions":{"view_html":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW","download_json":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW.json","view_paper":"https://pith.science/paper/AAQTUMOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.05042&json=true","fetch_graph":"https://pith.science/api/pith-number/AAQTUMOEEZMVE7PE6NNBEXTIIW/graph.json","fetch_events":"https://pith.science/api/pith-number/AAQTUMOEEZMVE7PE6NNBEXTIIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW/action/storage_attestation","attest_author":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW/action/author_attestation","sign_citation":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW/action/citation_signature","submit_replication":"https://pith.science/pith/AAQTUMOEEZMVE7PE6NNBEXTIIW/action/replication_record"}},"created_at":"2026-05-18T00:00:29.366051+00:00","updated_at":"2026-05-18T00:00:29.366051+00:00"}