{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:H7AR7XOTW5TKHTIIUXZVBFX6GA","short_pith_number":"pith:H7AR7XOT","schema_version":"1.0","canonical_sha256":"3fc11fddd3b766a3cd08a5f35096fe300a18691f6f8cbca5934bf2db9170ff8f","source":{"kind":"arxiv","id":"1705.04228","version":2},"attestation_state":"computed","paper":{"title":"Incremental Learning Through Deep Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Rosenfeld, John K. Tsotsos","submitted_at":"2017-05-11T15:04:10Z","abstract_excerpt":"Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a substantial increment in the number of parameters for each added domain, typically as many as the original network. We propose a method called \\emph{Deep Adaptation Networks} (DAN) that constrains newly learned filters to be linear combinations of existing ones. DANs precisely preserve performance on the original domain, require a fraction (typically 13\\%, depe"},"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":"1705.04228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-11T15:04:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be093427695524edf092287e37cfff9d17d3e8b284788e0c16f50da566f4d4d3","abstract_canon_sha256":"e3c452afdc935c266b89307ed958e61a35ff43c819af2dc08ee4ec8da2a1b66b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:23.278860Z","signature_b64":"xOXPKdlFczPc7uC193h6JmBan+MTcXgq4KiPbLDkkELCiAonmONUQTtTXnnjQ2mkTAeD/YKEQuZT7Nx4A8ifAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fc11fddd3b766a3cd08a5f35096fe300a18691f6f8cbca5934bf2db9170ff8f","last_reissued_at":"2026-05-18T00:23:23.278060Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:23.278060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Learning Through Deep Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Rosenfeld, John K. Tsotsos","submitted_at":"2017-05-11T15:04:10Z","abstract_excerpt":"Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a substantial increment in the number of parameters for each added domain, typically as many as the original network. We propose a method called \\emph{Deep Adaptation Networks} (DAN) that constrains newly learned filters to be linear combinations of existing ones. DANs precisely preserve performance on the original domain, require a fraction (typically 13\\%, depe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04228","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":"1705.04228","created_at":"2026-05-18T00:23:23.278194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.04228v2","created_at":"2026-05-18T00:23:23.278194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04228","created_at":"2026-05-18T00:23:23.278194+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7AR7XOTW5TK","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7AR7XOTW5TKHTII","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7AR7XOT","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10267","citing_title":"Efficient Multi-Domain Network Learning by Covariance Normalization","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA","json":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA.json","graph_json":"https://pith.science/api/pith-number/H7AR7XOTW5TKHTIIUXZVBFX6GA/graph.json","events_json":"https://pith.science/api/pith-number/H7AR7XOTW5TKHTIIUXZVBFX6GA/events.json","paper":"https://pith.science/paper/H7AR7XOT"},"agent_actions":{"view_html":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA","download_json":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA.json","view_paper":"https://pith.science/paper/H7AR7XOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.04228&json=true","fetch_graph":"https://pith.science/api/pith-number/H7AR7XOTW5TKHTIIUXZVBFX6GA/graph.json","fetch_events":"https://pith.science/api/pith-number/H7AR7XOTW5TKHTIIUXZVBFX6GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA/action/storage_attestation","attest_author":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA/action/author_attestation","sign_citation":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA/action/citation_signature","submit_replication":"https://pith.science/pith/H7AR7XOTW5TKHTIIUXZVBFX6GA/action/replication_record"}},"created_at":"2026-05-18T00:23:23.278194+00:00","updated_at":"2026-05-18T00:23:23.278194+00:00"}