Show simple item record  

dc.contributor.authorWang, Hongyuen_NZ
dc.contributor.authorGouk, Henryen_NZ
dc.contributor.authorFrank, Eibeen_NZ
dc.contributor.authorPfahringer, Bernharden_NZ
dc.contributor.authorMayo, Michaelen_NZ
dc.contributor.editorGallagher, M.en_NZ
dc.contributor.editorMoustafa, N.en_NZ
dc.contributor.editorLakshika, E.en_NZ
dc.coverage.spatialCanberra, Australiaen_NZ
dc.date.accessioned2020-12-15T20:35:16Z
dc.date.available2020-12-15T20:35:16Z
dc.date.issued2020en_NZ
dc.identifier.citationWang, H., Gouk, H., Frank, E., Pfahringer, B., & Mayo, M. (2020). A comparison of machine learning methods for cross-domain few-shot learning. In M. Gallagher, N. Moustafa, & E. Lakshika (Eds.), AI 2020: Advances in Artificial Intelligence. AI 2020. Lecture Notes in Computer Science (Vol. LNAI 12576, pp. 445–457). Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-030-64984-5_35en
dc.identifier.urihttps://hdl.handle.net/10289/14027
dc.description.abstractWe present an empirical evaluation of machine learning algorithms in cross-domain few-shot learning based on a fixed pre-trained feature extractor. Experiments were performed in five target domains (CropDisease, EuroSAT, Food101, ISIC and ChestX) and using two feature extractors: a ResNet10 model trained on a subset of ImageNet known as miniImageNet and a ResNet152 model trained on the ILSVRC 2012 subset of ImageNet. Commonly used machine learning algorithms including logistic regression, support vector machines, random forests, nearest neighbour classification, naïve Bayes, and linear and quadratic discriminant analysis were evaluated on the extracted feature vectors. We also evaluated classification accuracy when subjecting the feature vectors to normalisation using p-norms. Algorithms originally developed for the classification of gene expression data—the nearest shrunken centroid algorithm and LDA ensembles obtained with random projections—were also included in the experiments, in addition to a cosine similarity classifier that has recently proved popular in few-shot learning. The results enable us to identify algorithms, normalisation methods and pre-trained feature extractors that perform well in cross-domain few-shot learning. We show that the cosine similarity classifier and ℓ² -regularised 1-vs-rest logistic regression are generally the best-performing algorithms. We also show that algorithms such as LDA yield consistently higher accuracy when applied to ℓ² -normalised feature vectors. In addition, all classifiers generally perform better when extracting feature vectors using the ResNet152 model instead of the ResNet10 model.
dc.language.isoen
dc.publisherSpringeren_NZ
dc.rights© 2020 Springer Nature Switzerland AG. This is the author's accepted version. The final publication is available at Springer via dx.doi.org/10.1007/978-3-030-64984-5_35
dc.sourceAI 2020en_NZ
dc.subjectcomputer scienceen_NZ
dc.subjectcross-domain few-shot learningen_NZ
dc.subjectpre-trained feature extractorsen_NZ
dc.subjectnormalisationen_NZ
dc.subjecttransfer learningen_NZ
dc.subjectMachine learning
dc.titleA comparison of machine learning methods for cross-domain few-shot learningen_NZ
dc.typeConference Contribution
dc.identifier.doi10.1007/978-3-030-64984-5_35en_NZ
dc.relation.isPartOfAI 2020: Advances in Artificial Intelligence. AI 2020. Lecture Notes in Computer Scienceen_NZ
pubs.begin-page445
pubs.elements-id258450
pubs.end-page457
pubs.finish-date2020-11-30en_NZ
pubs.place-of-publicationChamen_NZ
pubs.place-of-publicationCham, Switzerland
pubs.start-date2020-11-29en_NZ
pubs.volumeLNAI 12576en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record