A Comparison of Machine Learning Methods for Cross-Domain Few-Shot Learning

Hongyu Wang, Henry Gouk, Eibe Frank, Bernhard Pfahringer, Michael Mayo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We 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 thec lassification 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.
Original languageEnglish
Title of host publicationAI 2020: Advances in Artificial Intelligence
PublisherSpringer, Cham
Number of pages13
ISBN (Electronic)978-3-030-64984-5
ISBN (Print)978-3-030-64983-8
Publication statusPublished - 27 Nov 2020
Event33rd Australasian Joint Conference on Artificial Intelligence - Virtual Conference
Duration: 29 Nov 202030 Nov 2020

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference33rd Australasian Joint Conference on Artificial Intelligence
Abbreviated titleAI 2020
CityVirtual Conference
Internet address

Keywords / Materials (for Non-textual outputs)

  • Cross-Domain Few-Shot Learning
  • Pre-trained Feature Extractors
  • Normalisation
  • Transfer Learning


Dive into the research topics of 'A Comparison of Machine Learning Methods for Cross-Domain Few-Shot Learning'. Together they form a unique fingerprint.

Cite this