You can read the paper here - https://lnkd.in/ddHKQ4v5
Checkout the code - https://github.com/ArmanAfrasiyabi/Mi...

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.

About the speaker :
Arman Afrasiyabi is a final-year Ph.D. student at Mila, and in the Department of Electrical Engineering and Computer Engineering at Université Laval. With his supervisors, they first proposed the idea of associative alignment for few-shot image classification at the European Conference on Computer Vision (ECCV) 2020. Then, they present a mixture of model-based representation learning approaches at the International Conference on Computer Vision (ICCV) 2021. He also completed the third Ph.D. project in collaboration with Prof. Hugo Larochelle, which is under review now. Before the Ph.D., Arman was an M.S. student at biomedical and computer engineering and worked on two projects on medical image analysis using machine learning.