Flexible Few-Shot Learning with Contextual Similarity

by   Mengye Ren, et al.

Existing approaches to few-shot learning deal with tasks that have persistent, rigid notions of classes. Typically, the learner observes data only from a fixed number of classes at training time and is asked to generalize to a new set of classes at test time. Two examples from the same class would always be assigned the same labels in any episode. In this work, we consider a realistic setting where the similarities between examples can change from episode to episode depending on the task context, which is not given to the learner. We define new benchmark datasets for this flexible few-shot scenario, where the tasks are based on images of faces (Celeb-A), shoes (Zappos50K), and general objects (ImageNet-with-Attributes). While classification baselines and episodic approaches learn representations that work well for standard few-shot learning, they suffer in our flexible tasks as novel similarity definitions arise during testing. We propose to build upon recent contrastive unsupervised learning techniques and use a combination of instance and class invariance learning, aiming to obtain general and flexible features. We find that our approach performs strongly on our new flexible few-shot learning benchmarks, demonstrating that unsupervised learning obtains more generalizable representations.


page 11

page 24

page 25

page 28


Few-shot Learning with Meta Metric Learners

Few-shot Learning aims to learn classifiers for new classes with only a ...

Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning

Deep learning has shown great success in settings with massive amounts o...

Unsupervised Few-shot Learning via Self-supervised Training

Learning from limited exemplars (few-shot learning) is a fundamental, un...

The Boundary Forest Algorithm for Online Supervised and Unsupervised Learning

We describe a new instance-based learning algorithm called the Boundary ...

Wandering Within a World: Online Contextualized Few-Shot Learning

We aim to bridge the gap between typical human and machine-learning envi...

Memory Matching Networks for One-Shot Image Recognition

In this paper, we introduce the new ideas of augmenting Convolutional Ne...

Function Contrastive Learning of Transferable Representations

Few-shot-learning seeks to find models that are capable of fast-adaptati...