{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:YLNWOG6DKAKPGVCSEXAVBZ7GWN","short_pith_number":"pith:YLNWOG6D","schema_version":"1.0","canonical_sha256":"c2db671bc35014f3545225c150e7e6b372a017e8d4b1770cb37b23a532a67de0","source":{"kind":"arxiv","id":"1412.3474","version":1},"attestation_state":"computed","paper":{"title":"Deep Domain Confusion: Maximizing for Domain Invariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Tzeng, Judy Hoffman, Kate Saenko, Ning Zhang, Trevor Darrell","submitted_at":"2014-12-10T21:20:54Z","abstract_excerpt":"Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the di"},"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":"1412.3474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-10T21:20:54Z","cross_cats_sorted":[],"title_canon_sha256":"fbd1114130fd3de758d74d9440c317f58671d1d8ff79000df163a9d5b4e4bdf4","abstract_canon_sha256":"076781e0661dbdee64dd8f3dc9470c5c4cfb9d291f0b1d817d216599dbc0ce3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:36.506642Z","signature_b64":"CBTx77Z/vdNr6WzGFkS4cjf4TlD7aKuSMj/ID1wgNyq9QeGOve8hR/v2C5+0w6NzNC7l1Gn+Y0Gy8ucHl8iiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2db671bc35014f3545225c150e7e6b372a017e8d4b1770cb37b23a532a67de0","last_reissued_at":"2026-05-18T02:31:36.506037Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:36.506037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Domain Confusion: Maximizing for Domain Invariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Tzeng, Judy Hoffman, Kate Saenko, Ning Zhang, Trevor Darrell","submitted_at":"2014-12-10T21:20:54Z","abstract_excerpt":"Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.3474","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":"1412.3474","created_at":"2026-05-18T02:31:36.506127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.3474v1","created_at":"2026-05-18T02:31:36.506127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.3474","created_at":"2026-05-18T02:31:36.506127+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLNWOG6DKAKP","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLNWOG6DKAKPGVCS","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLNWOG6D","created_at":"2026-05-18T12:28:57.508820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1907.00612","citing_title":"One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07480","citing_title":"Remaining Useful Lifetime Prediction via Deep Domain Adaptation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11004","citing_title":"Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11740","citing_title":"Environment Probing Interaction Policies","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2512.05226","citing_title":"Variance Matters: Improving Domain Adaptation via Stratified Sampling","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2603.26931","citing_title":"Tunable Domain Adaptation Using Unfolding","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03787","citing_title":"A Robust Unsupervised Domain Adaptation Framework for Medical Image Classification Using RKHS-MMD","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05730","citing_title":"Effective Knowledge Transfer for Multi-Task Recommendation Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23790","citing_title":"A General Representation-Based Approach to Multi-Source Domain Adaptation","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00906","citing_title":"Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09863","citing_title":"PAS: Estimating the target accuracy before domain adaptation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03085","citing_title":"Adaptive Data Compression and Reconstruction for Memory-Bounded EEG Continual Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN","json":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN.json","graph_json":"https://pith.science/api/pith-number/YLNWOG6DKAKPGVCSEXAVBZ7GWN/graph.json","events_json":"https://pith.science/api/pith-number/YLNWOG6DKAKPGVCSEXAVBZ7GWN/events.json","paper":"https://pith.science/paper/YLNWOG6D"},"agent_actions":{"view_html":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN","download_json":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN.json","view_paper":"https://pith.science/paper/YLNWOG6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.3474&json=true","fetch_graph":"https://pith.science/api/pith-number/YLNWOG6DKAKPGVCSEXAVBZ7GWN/graph.json","fetch_events":"https://pith.science/api/pith-number/YLNWOG6DKAKPGVCSEXAVBZ7GWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN/action/storage_attestation","attest_author":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN/action/author_attestation","sign_citation":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN/action/citation_signature","submit_replication":"https://pith.science/pith/YLNWOG6DKAKPGVCSEXAVBZ7GWN/action/replication_record"}},"created_at":"2026-05-18T02:31:36.506127+00:00","updated_at":"2026-05-18T02:31:36.506127+00:00"}