{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YNHDQQWNUNDSEC6OWNZ6KV3IXT","short_pith_number":"pith:YNHDQQWN","schema_version":"1.0","canonical_sha256":"c34e3842cda347220bceb373e55768bcddacdf319ed9ad456d645c7a05aac5ec","source":{"kind":"arxiv","id":"2106.05152","version":8},"attestation_state":"computed","paper":{"title":"Rethinking Transfer Learning for Medical Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Gaoxiang Luo, Hengyue Liang, Ju Sun, Le Peng, Taihui Li","submitted_at":"2021-06-09T15:51:03Z","abstract_excerpt":"Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained models may be suboptimal. This insight has partly motivated the recent differential TL strategies, such as TransFusion (TF) and layer-wise finetuning (LWFT), which treat the layers in the pretrained models differentially. In this paper, we add one more strategy into this family, called TruncatedTL, which reuses and finetunes appropriate bottom layers and dire"},"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":"2106.05152","kind":"arxiv","version":8},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2021-06-09T15:51:03Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"de2a7fed37a66ee67b173ef410713c932e01a6f3816816c04d4525fb77541421","abstract_canon_sha256":"add3c770cbbf91e2f14d80d502f04166fe09afbd022efa111797d8fa08549008"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:05.869569Z","signature_b64":"qMPKouEFpdlSokd1qz2QwR22XlTh/Uzo6GJhFf6n/nTasqu6gyVwfemDbx62lJo8sthIrsjwcAXuD05Tt2ANDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c34e3842cda347220bceb373e55768bcddacdf319ed9ad456d645c7a05aac5ec","last_reissued_at":"2026-07-05T08:23:05.869075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:05.869075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Transfer Learning for Medical Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Gaoxiang Luo, Hengyue Liang, Ju Sun, Le Peng, Taihui Li","submitted_at":"2021-06-09T15:51:03Z","abstract_excerpt":"Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained models may be suboptimal. This insight has partly motivated the recent differential TL strategies, such as TransFusion (TF) and layer-wise finetuning (LWFT), which treat the layers in the pretrained models differentially. In this paper, we add one more strategy into this family, called TruncatedTL, which reuses and finetunes appropriate bottom layers and dire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05152","kind":"arxiv","version":8},"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/2106.05152/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":"2106.05152","created_at":"2026-07-05T08:23:05.869133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.05152v8","created_at":"2026-07-05T08:23:05.869133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05152","created_at":"2026-07-05T08:23:05.869133+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNHDQQWNUNDS","created_at":"2026-07-05T08:23:05.869133+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNHDQQWNUNDSEC6O","created_at":"2026-07-05T08:23:05.869133+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNHDQQWN","created_at":"2026-07-05T08:23:05.869133+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/YNHDQQWNUNDSEC6OWNZ6KV3IXT","json":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT.json","graph_json":"https://pith.science/api/pith-number/YNHDQQWNUNDSEC6OWNZ6KV3IXT/graph.json","events_json":"https://pith.science/api/pith-number/YNHDQQWNUNDSEC6OWNZ6KV3IXT/events.json","paper":"https://pith.science/paper/YNHDQQWN"},"agent_actions":{"view_html":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT","download_json":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT.json","view_paper":"https://pith.science/paper/YNHDQQWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.05152&json=true","fetch_graph":"https://pith.science/api/pith-number/YNHDQQWNUNDSEC6OWNZ6KV3IXT/graph.json","fetch_events":"https://pith.science/api/pith-number/YNHDQQWNUNDSEC6OWNZ6KV3IXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT/action/storage_attestation","attest_author":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT/action/author_attestation","sign_citation":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT/action/citation_signature","submit_replication":"https://pith.science/pith/YNHDQQWNUNDSEC6OWNZ6KV3IXT/action/replication_record"}},"created_at":"2026-07-05T08:23:05.869133+00:00","updated_at":"2026-07-05T08:23:05.869133+00:00"}