Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

02/09/2021
by   Tomáš Chobola, et al.
0

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.

READ FULL TEXT
research
06/06/2020

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

Few-shot classification is a challenging problem due to the uncertainty ...
research
09/16/2018

Latent Space Optimal Transport for Generative Models

Variational Auto-Encoders enforce their learned intermediate latent-spac...
research
06/18/2020

Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models

Unsupervised meta-learning approaches rely on synthetic meta-tasks that ...
research
11/01/2022

Meta-Learning for Unsupervised Outlier Detection with Optimal Transport

Automated machine learning has been widely researched and adopted in the...
research
01/11/2022

Entropic Optimal Transport in Random Graphs

In graph analysis, a classic task consists in computing similarity measu...
research
05/04/2022

Immiscible Color Flows in Optimal Transport Networks for Image Classification

In classification tasks, it is crucial to meaningfully exploit informati...
research
05/26/2012

On latent position inference from doubly stochastic messaging activities

We model messaging activities as a hierarchical doubly stochastic point ...

Please sign up or login with your details

Forgot password? Click here to reset