{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZTOKM7YBNIMP6ATGHH33KHIQBP","short_pith_number":"pith:ZTOKM7YB","schema_version":"1.0","canonical_sha256":"ccdca67f016a18ff026639f7b51d100bed6ec917525bafca1053f5d48e2a5cce","source":{"kind":"arxiv","id":"1711.01575","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Dropout Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Kuniaki Saito, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2017-11-05T12:26:09Z","abstract_excerpt":"We present a method for transferring neural representations from label-rich source domains to unlabeled target domains. Recent adversarial methods proposed for this task learn to align features across domains by fooling a special domain critic network. However, a drawback of this approach is that the critic simply labels the generated features as in-domain or not, without considering the boundaries between classes. This can lead to ambiguous features being generated near class boundaries, reducing target classification accuracy. We propose a novel approach, Adversarial Dropout Regularization ("},"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":"1711.01575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-05T12:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"0805841f4e201bdf601003ea1b33dd8d07681533f1711a059a3e4a31d1480848","abstract_canon_sha256":"88d59ec8c600bbfdf45e00e5ddeb9db01bee185e731fe8648dff21e1ace2e504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:10.582692Z","signature_b64":"4LEbPO9ju0WhHE9V4fUwNrvSsBNP4HO3UG3LD+qVGsFPDl7ZwDndH0NrqIR43N338WTUtY9gbGxvtwQqhamWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccdca67f016a18ff026639f7b51d100bed6ec917525bafca1053f5d48e2a5cce","last_reissued_at":"2026-05-18T00:22:10.582176Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:10.582176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Dropout Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kate Saenko, Kuniaki Saito, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2017-11-05T12:26:09Z","abstract_excerpt":"We present a method for transferring neural representations from label-rich source domains to unlabeled target domains. Recent adversarial methods proposed for this task learn to align features across domains by fooling a special domain critic network. However, a drawback of this approach is that the critic simply labels the generated features as in-domain or not, without considering the boundaries between classes. This can lead to ambiguous features being generated near class boundaries, reducing target classification accuracy. We propose a novel approach, Adversarial Dropout Regularization ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01575","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":""},"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":"1711.01575","created_at":"2026-05-18T00:22:10.582266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01575v3","created_at":"2026-05-18T00:22:10.582266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01575","created_at":"2026-05-18T00:22:10.582266+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTOKM7YBNIMP","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTOKM7YBNIMP6ATG","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTOKM7YB","created_at":"2026-05-18T12:31:59.375834+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/ZTOKM7YBNIMP6ATGHH33KHIQBP","json":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP.json","graph_json":"https://pith.science/api/pith-number/ZTOKM7YBNIMP6ATGHH33KHIQBP/graph.json","events_json":"https://pith.science/api/pith-number/ZTOKM7YBNIMP6ATGHH33KHIQBP/events.json","paper":"https://pith.science/paper/ZTOKM7YB"},"agent_actions":{"view_html":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP","download_json":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP.json","view_paper":"https://pith.science/paper/ZTOKM7YB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01575&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTOKM7YBNIMP6ATGHH33KHIQBP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTOKM7YBNIMP6ATGHH33KHIQBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP/action/storage_attestation","attest_author":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP/action/author_attestation","sign_citation":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP/action/citation_signature","submit_replication":"https://pith.science/pith/ZTOKM7YBNIMP6ATGHH33KHIQBP/action/replication_record"}},"created_at":"2026-05-18T00:22:10.582266+00:00","updated_at":"2026-05-18T00:22:10.582266+00:00"}