{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZR3DZLA3TOGDOCIFTXOOKYMYCU","short_pith_number":"pith:ZR3DZLA3","schema_version":"1.0","canonical_sha256":"cc763cac1b9b8c3709059ddce56198150488cf0176fcce11fb2453ee53b34523","source":{"kind":"arxiv","id":"2107.08585","version":2},"attestation_state":"computed","paper":{"title":"Non-binary deep transfer learning for image classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jo Plested, Tom Gedeon, Xuyang Shen","submitted_at":"2021-07-19T02:34:38Z","abstract_excerpt":"The current standard for a variety of computer vision tasks using smaller numbers of labelled training examples is to fine-tune from weights pre-trained on a large image classification dataset such as ImageNet. The application of transfer learning and transfer learning methods tends to be rigidly binary. A model is either pre-trained or not pre-trained. Pre-training a model either increases performance or decreases it, the latter being defined as negative transfer. Application of L2-SP regularisation that decays the weights towards their pre-trained values is either applied or all weights are "},"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":"2107.08585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-19T02:34:38Z","cross_cats_sorted":[],"title_canon_sha256":"d552c1dfd511d4517fb826915cec6f4942785077d5ade9250822a063b38f4993","abstract_canon_sha256":"b45bf6031444779d4008e9154981747bca14e1c4d069436d33e83444e004d8f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:46.872886Z","signature_b64":"0hbND/iMpRShE4cVbLMYyi9YxNwJLQv3ebDSZnjs1B+Gz765DdYmu3sxqRVqc6SxifgLIZat6j74LvqXf8OzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc763cac1b9b8c3709059ddce56198150488cf0176fcce11fb2453ee53b34523","last_reissued_at":"2026-07-05T03:09:46.872328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:46.872328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-binary deep transfer learning for image classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jo Plested, Tom Gedeon, Xuyang Shen","submitted_at":"2021-07-19T02:34:38Z","abstract_excerpt":"The current standard for a variety of computer vision tasks using smaller numbers of labelled training examples is to fine-tune from weights pre-trained on a large image classification dataset such as ImageNet. The application of transfer learning and transfer learning methods tends to be rigidly binary. A model is either pre-trained or not pre-trained. Pre-training a model either increases performance or decreases it, the latter being defined as negative transfer. Application of L2-SP regularisation that decays the weights towards their pre-trained values is either applied or all weights are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08585","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.08585/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":"2107.08585","created_at":"2026-07-05T03:09:46.872388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08585v2","created_at":"2026-07-05T03:09:46.872388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08585","created_at":"2026-07-05T03:09:46.872388+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZR3DZLA3TOGD","created_at":"2026-07-05T03:09:46.872388+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZR3DZLA3TOGDOCIF","created_at":"2026-07-05T03:09:46.872388+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZR3DZLA3","created_at":"2026-07-05T03:09:46.872388+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/ZR3DZLA3TOGDOCIFTXOOKYMYCU","json":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU.json","graph_json":"https://pith.science/api/pith-number/ZR3DZLA3TOGDOCIFTXOOKYMYCU/graph.json","events_json":"https://pith.science/api/pith-number/ZR3DZLA3TOGDOCIFTXOOKYMYCU/events.json","paper":"https://pith.science/paper/ZR3DZLA3"},"agent_actions":{"view_html":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU","download_json":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU.json","view_paper":"https://pith.science/paper/ZR3DZLA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08585&json=true","fetch_graph":"https://pith.science/api/pith-number/ZR3DZLA3TOGDOCIFTXOOKYMYCU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZR3DZLA3TOGDOCIFTXOOKYMYCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU/action/storage_attestation","attest_author":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU/action/author_attestation","sign_citation":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU/action/citation_signature","submit_replication":"https://pith.science/pith/ZR3DZLA3TOGDOCIFTXOOKYMYCU/action/replication_record"}},"created_at":"2026-07-05T03:09:46.872388+00:00","updated_at":"2026-07-05T03:09:46.872388+00:00"}