Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
This work addresses the problem of limited labeled data in image classification for machine learning practitioners, though it is incremental as it builds on existing meta-learning and optimal transport techniques.
The paper tackled few-shot image classification by aligning class distributions in a latent space using optimal transport mapping, achieving second place in the MetaDL Challenge 2020 and outperforming previous methods.
MetaDL Challenge 2020 focused on image classification tasks in few-shot settings. This paper describes second best submission in the competition. Our meta learning approach modifies the distribution of classes in a latent space produced by a backbone network for each class in order to better follow the Gaussian distribution. After this operation which we call Latent Space Transform algorithm, centers of classes are further aligned in an iterative fashion of the Expectation Maximisation algorithm to utilize information in unlabeled data that are often provided on top of few labelled instances. For this task, we utilize optimal transport mapping using the Sinkhorn algorithm. Our experiments show that this approach outperforms previous works as well as other variants of the algorithm, using K-Nearest Neighbour algorithm, Gaussian Mixture Models, etc.