{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KQHFRB2JXTWTYCFBIMALLQ7HLX","short_pith_number":"pith:KQHFRB2J","schema_version":"1.0","canonical_sha256":"540e588749bced3c08a14300b5c3e75de4f9dd6a7f8c507c75a9a2acbed60399","source":{"kind":"arxiv","id":"2006.03806","version":3},"attestation_state":"computed","paper":{"title":"Leveraging the Feature Distribution in Transfer-based Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"St\\'ephane Pateux, Vincent Gripon, Yuqing Hu","submitted_at":"2020-06-06T07:32:08Z","abstract_excerpt":"Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance. Following this vein, in this paper we propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm (in the case of transductive "},"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":"2006.03806","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-06T07:32:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"192a5ffa66dc9d477cefa9259fcba71554614b364dac1d7c66425105ad72a1a6","abstract_canon_sha256":"bf64b1b1c50d37c7f015747745f8496ea041f09c201179a89e966bf22f9c240b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:40.648795Z","signature_b64":"L1qisS8oxHzdp4CxPkmN1dL2V8YvDwl/jGsIAmrYwCOUYUrtnGl7aCX7wPknYb4+MOJTBi8c8Qo4lMP+LYTZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"540e588749bced3c08a14300b5c3e75de4f9dd6a7f8c507c75a9a2acbed60399","last_reissued_at":"2026-07-05T02:09:40.648278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:40.648278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging the Feature Distribution in Transfer-based Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"St\\'ephane Pateux, Vincent Gripon, Yuqing Hu","submitted_at":"2020-06-06T07:32:08Z","abstract_excerpt":"Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance. Following this vein, in this paper we propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm (in the case of transductive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03806","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/2006.03806/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":"2006.03806","created_at":"2026-07-05T02:09:40.648343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.03806v3","created_at":"2026-07-05T02:09:40.648343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03806","created_at":"2026-07-05T02:09:40.648343+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQHFRB2JXTWT","created_at":"2026-07-05T02:09:40.648343+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQHFRB2JXTWTYCFB","created_at":"2026-07-05T02:09:40.648343+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQHFRB2J","created_at":"2026-07-05T02:09:40.648343+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/KQHFRB2JXTWTYCFBIMALLQ7HLX","json":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX.json","graph_json":"https://pith.science/api/pith-number/KQHFRB2JXTWTYCFBIMALLQ7HLX/graph.json","events_json":"https://pith.science/api/pith-number/KQHFRB2JXTWTYCFBIMALLQ7HLX/events.json","paper":"https://pith.science/paper/KQHFRB2J"},"agent_actions":{"view_html":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX","download_json":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX.json","view_paper":"https://pith.science/paper/KQHFRB2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.03806&json=true","fetch_graph":"https://pith.science/api/pith-number/KQHFRB2JXTWTYCFBIMALLQ7HLX/graph.json","fetch_events":"https://pith.science/api/pith-number/KQHFRB2JXTWTYCFBIMALLQ7HLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX/action/storage_attestation","attest_author":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX/action/author_attestation","sign_citation":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX/action/citation_signature","submit_replication":"https://pith.science/pith/KQHFRB2JXTWTYCFBIMALLQ7HLX/action/replication_record"}},"created_at":"2026-07-05T02:09:40.648343+00:00","updated_at":"2026-07-05T02:09:40.648343+00:00"}