Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning

by   Peyman Bateni, et al.

Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examples. In previously proposed few-shot visual classifiers, it is assumed that the feature manifold, where classifier decisions are made, has uncorrelated feature dimensions and uniform feature variance. In this work, we focus on addressing the limitations arising from this assumption by proposing a variance-sensitive class of models that operates in a low-label regime. The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks. We further extend this approach to a transductive learning setting, proposing Transductive CNAPS. This transductive method combines a soft k-means parameter refinement procedure with a two-step task encoder to achieve improved test-time classification accuracy using unlabelled data. Transductive CNAPS achieves state of the art performance on Meta-Dataset. Finally, we explore the use of our methods (Simple and Transductive) for "out of the box" continual and active learning. Extensive experiments on large scale benchmarks illustrate robustness and versatility of this, relatively speaking, simple class of models. All trained model checkpoints and corresponding source codes have been made publicly available.


page 1

page 4

page 5

page 15

page 18

page 19


Improving Few-Shot Visual Classification with Unlabelled Examples

We propose a transductive meta-learning method that uses unlabelled inst...

Trainable Class Prototypes for Few-Shot Learning

Metric learning is a widely used method for few shot learning in which t...

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

The goal of this paper is to design image classification systems that, a...

Diversity with Cooperation: Ensemble Methods for Few-Shot Classification

Few-shot classification consists of learning a predictive model that is ...

The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence

Recently, it has been observed that a transfer learning solution might b...

Transductive Few-Shot Classification on the Oblique Manifold

Few-shot learning (FSL) attempts to learn with limited data. In this wor...

Dual Adversarial Alignment for Realistic Support-Query Shift Few-shot Learning

Support-query shift few-shot learning aims to classify unseen examples (...

Please sign up or login with your details

Forgot password? Click here to reset