https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/Head https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://www.nanopub.org/nschema#hasAssertion https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/assertion https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://www.nanopub.org/nschema#hasProvenance https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/provenance https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/pubinfo https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/assertion https://doi.org/10.1007/978-3-030-58583-9_8 http://purl.org/spar/cito/hasQuotedText The results demonstrate that state-of-art meta-learning methods are surprisingly outperformed by earlier meta-learning approaches, and all meta-learning methods underperform in relation to simple fine-tuning by 12.8% average accuracy. https://doi.org/10.1007/978-3-030-58583-9_8 http://www.w3.org/2000/01/rdf-schema#comment This finding has important implications for Earth observation. If simple fine tuning outperforms complex meta learning for cross domain few shot classification, environmental scientists working with limited labeled satellite data can rely on standard supervised learning. This applies to tasks like habitat monitoring, land cover change, and biodiversity assessment, lowering the barrier to using AI in environmental research. https://w3id.org/np/o/ntemplate/CREATOR http://purl.org/spar/cito/quotes https://doi.org/10.1007/978-3-030-58583-9_8 https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/provenance https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/assertion http://www.w3.org/ns/prov#wasAttributedTo https://orcid.org/0000-0002-1784-2920 https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/pubinfo https://orcid.org/0000-0002-1784-2920 http://xmlns.com/foaf/0.1/name Anne Fouilloux https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://purl.org/dc/terms/created 2026-04-18T14:58:01.411Z https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://purl.org/dc/terms/creator https://orcid.org/0000-0002-1784-2920 https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://purl.org/dc/terms/license https://creativecommons.org/licenses/by/4.0/ https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://purl.org/nanopub/x/hasNanopubType http://purl.org/spar/cito/cites https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://purl.org/nanopub/x/wasCreatedAt https://platform.sciencelive4all.org https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 http://www.w3.org/2000/01/rdf-schema#label Paper annotation: The results demonstrate that state-of-art meta-learning methods are surprisingly outperformed by earlier meta-learning approaches, and all meta-learning methods underperform in relation to simple fine-tuning by 12.8% average accuracy. https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 https://w3id.org/np/o/ntemplate/wasCreatedFromTemplate https://w3id.org/np/RA24onqmqTMsraJ7ypYFOuckmNWpo4Zv5gsLqhXt7xYPU https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/sig http://purl.org/nanopub/x/hasPublicKey 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 https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/sig http://purl.org/nanopub/x/hasSignature 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 https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4 https://w3id.org/sciencelive/np/RA-bVr4LQBaoZPSWEyLFLWdoC7BTcObJ6ykgtBSml5cp4/sig http://purl.org/nanopub/x/signedBy https://orcid.org/0000-0002-1784-2920