Mixture-based Feature Space Learning for Few-shot Image Classification
Arman Afrasiyabi     Jean-François Lalonde     Christian Gagné    




[Paper]
[GitHub]
[Video]

Accepted at International Conference on Computer Vision (ICCV), 2021!


Abstract

We introduce Mixture-based Feature Space Learning (MixtFSL) for obtaining a rich and robust feature representation in the context of few-shot image classification. Previous works have proposed to model each base class either with a single point or with a mixture model by relying on offline clustering algorithms. In contrast, we propose to model base classes with mixture models by simultaneously training the feature extractor and learning the mixture model parameters in an online manner. This results in a richer and more discriminative feature space which can be employed to classify novel examples from very few samples. Two main stages are proposed to train the MixtFSL model. First, the multimodal mixtures for each base class and the feature extractor parameters are learned using a combination of two loss functions. Second, the resulting network and mixture models are progressively refined through a leader-follower learning procedure, which uses the current estimate as a “target network”. This target network is used to make a consistent assignment of instances to mixture components, which increases performance and stabilizes training. The effectiveness of our end-to-end feature space learning approach is demonstrated with extensive experiments on four standard datasets and four backbones.


Paper and Supplementary Material

Arman Afrasiyabi, Jean-François Lalonde, Christian Gagné
Mixture-based Feature Space Learning for Few-shot Image Classification.
(hosted on ArXiv)


[Bibtex]

Video [Slides]




Code


 [GitHub]



Poster


click on the figure to see .pdf version.


Acknowledgements

This project was supported by funding from NSERC-Canada, Mitacs, Prompt-Québec, and E Machine Learning.