{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5GQBO664NKQYAZAN67OVVC2OMQ","short_pith_number":"pith:5GQBO664","schema_version":"1.0","canonical_sha256":"e9a0177bdc6aa180640df7dd5a8b4e641dcf68af45547219419afce19ac4c496","source":{"kind":"arxiv","id":"2006.12009","version":1},"attestation_state":"computed","paper":{"title":"Feature Alignment and Restoration for Domain Generalization and Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cuiling Lan, Wenjun Zeng, Xin Jin, Zhibo Chen","submitted_at":"2020-06-22T05:08:13Z","abstract_excerpt":"For domain generalization (DG) and unsupervised domain adaptation (UDA), cross domain feature alignment has been widely explored to pull the feature distributions of different domains in order to learn domain-invariant representations. However, the feature alignment is in general task-ignorant and could result in degradation of the discrimination power of the feature representation and thus hinders the high performance. In this paper, we propose a unified framework termed Feature Alignment and Restoration (FAR) to simultaneously ensure high generalization and discrimination power of the networ"},"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":"2006.12009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-22T05:08:13Z","cross_cats_sorted":[],"title_canon_sha256":"9872b9fccc96adc207483addf6262429fb750aefd23275e9dff9818990d3ff5f","abstract_canon_sha256":"0008e65fafdcb2a49284737bc66c55c4b9718295614b14a9f4712e59407571ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:56.250815Z","signature_b64":"ARACitMJpAjqrQsrlhrRknOfYUAF64YAmGSNaXE3/hNWM+99XG9fl42RjMcgRV6Hp52grBxdPwx1OmhvpaviAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9a0177bdc6aa180640df7dd5a8b4e641dcf68af45547219419afce19ac4c496","last_reissued_at":"2026-07-05T01:11:56.250389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:56.250389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Alignment and Restoration for Domain Generalization and Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cuiling Lan, Wenjun Zeng, Xin Jin, Zhibo Chen","submitted_at":"2020-06-22T05:08:13Z","abstract_excerpt":"For domain generalization (DG) and unsupervised domain adaptation (UDA), cross domain feature alignment has been widely explored to pull the feature distributions of different domains in order to learn domain-invariant representations. However, the feature alignment is in general task-ignorant and could result in degradation of the discrimination power of the feature representation and thus hinders the high performance. In this paper, we propose a unified framework termed Feature Alignment and Restoration (FAR) to simultaneously ensure high generalization and discrimination power of the networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12009","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.12009/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":"2006.12009","created_at":"2026-07-05T01:11:56.250446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12009v1","created_at":"2026-07-05T01:11:56.250446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12009","created_at":"2026-07-05T01:11:56.250446+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GQBO664NKQY","created_at":"2026-07-05T01:11:56.250446+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GQBO664NKQYAZAN","created_at":"2026-07-05T01:11:56.250446+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GQBO664","created_at":"2026-07-05T01:11:56.250446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11131","citing_title":"UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ","json":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ.json","graph_json":"https://pith.science/api/pith-number/5GQBO664NKQYAZAN67OVVC2OMQ/graph.json","events_json":"https://pith.science/api/pith-number/5GQBO664NKQYAZAN67OVVC2OMQ/events.json","paper":"https://pith.science/paper/5GQBO664"},"agent_actions":{"view_html":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ","download_json":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ.json","view_paper":"https://pith.science/paper/5GQBO664","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12009&json=true","fetch_graph":"https://pith.science/api/pith-number/5GQBO664NKQYAZAN67OVVC2OMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5GQBO664NKQYAZAN67OVVC2OMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ/action/storage_attestation","attest_author":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ/action/author_attestation","sign_citation":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ/action/citation_signature","submit_replication":"https://pith.science/pith/5GQBO664NKQYAZAN67OVVC2OMQ/action/replication_record"}},"created_at":"2026-07-05T01:11:56.250446+00:00","updated_at":"2026-07-05T01:11:56.250446+00:00"}