{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SJ4ISYSJ4XT4KOL25GUYOBDTCQ","short_pith_number":"pith:SJ4ISYSJ","schema_version":"1.0","canonical_sha256":"9278896249e5e7c5397ae9a98704731424cee767988cad74b8d06d579feb9e21","source":{"kind":"arxiv","id":"1911.10807","version":3},"attestation_state":"computed","paper":{"title":"Generalized Adaptation for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinlu Liu, Liang Song, Yongqiang Qin","submitted_at":"2019-11-25T10:18:37Z","abstract_excerpt":"Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model. In this paper, we propose to use closed-form base learner, which constrains the adapting stage with pre-trained base model to get better generalized novel model. Following theoretical analysis proves its rationality as well as indication of how to train a well-generalized base model. We then conduct experiments on four benchmarks and achieve state-of-the-art performance in all cases. Notably, we achieve the accuracy of 87.75% on 5-shot miniImageNet which approximately outperforms existin"},"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":"1911.10807","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-25T10:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"aaeba82bf72356f3beb199b18fd9bd2766fd5b60fd4854b5ae28b059c60a48df","abstract_canon_sha256":"1d95bdba4e324be7d375fc73c5c400b8fc16dc7b12ffdd3b33f783a960602912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:12.020686Z","signature_b64":"uKgKSXSvfEuFULXmdH/tiuPyYn24xKFaysjzd16+KojJoTiE9PtgrpV2bnTEcVIjl/lzF1UUUrr4A34zMP8UAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9278896249e5e7c5397ae9a98704731424cee767988cad74b8d06d579feb9e21","last_reissued_at":"2026-07-05T01:07:12.020189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:12.020189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Adaptation for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinlu Liu, Liang Song, Yongqiang Qin","submitted_at":"2019-11-25T10:18:37Z","abstract_excerpt":"Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model. In this paper, we propose to use closed-form base learner, which constrains the adapting stage with pre-trained base model to get better generalized novel model. Following theoretical analysis proves its rationality as well as indication of how to train a well-generalized base model. We then conduct experiments on four benchmarks and achieve state-of-the-art performance in all cases. Notably, we achieve the accuracy of 87.75% on 5-shot miniImageNet which approximately outperforms existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.10807","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.10807/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":"1911.10807","created_at":"2026-07-05T01:07:12.020255+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.10807v3","created_at":"2026-07-05T01:07:12.020255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.10807","created_at":"2026-07-05T01:07:12.020255+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJ4ISYSJ4XT4","created_at":"2026-07-05T01:07:12.020255+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJ4ISYSJ4XT4KOL2","created_at":"2026-07-05T01:07:12.020255+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJ4ISYSJ","created_at":"2026-07-05T01:07:12.020255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09299","citing_title":"ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ","json":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ.json","graph_json":"https://pith.science/api/pith-number/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/graph.json","events_json":"https://pith.science/api/pith-number/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/events.json","paper":"https://pith.science/paper/SJ4ISYSJ"},"agent_actions":{"view_html":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ","download_json":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ.json","view_paper":"https://pith.science/paper/SJ4ISYSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.10807&json=true","fetch_graph":"https://pith.science/api/pith-number/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/action/storage_attestation","attest_author":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/action/author_attestation","sign_citation":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/action/citation_signature","submit_replication":"https://pith.science/pith/SJ4ISYSJ4XT4KOL25GUYOBDTCQ/action/replication_record"}},"created_at":"2026-07-05T01:07:12.020255+00:00","updated_at":"2026-07-05T01:07:12.020255+00:00"}