Few-shot Learning with Meta Metric Learners

01/26/2019
by   Yu Cheng, et al.
8

Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various number of labels. The meta-learning approaches train a meta learner to predict weights of homogeneous-structured task-specific networks, requiring a uniform number of classes across tasks. The metric-learning approaches learn one task-invariant metric for all the tasks, and they fail if the tasks diverge. We propose to deal with these limitations with meta metric learning. Our meta metric learning approach consists of task-specific learners, that exploit metric learning to handle flexible labels, and a meta learner, that discovers good parameters and gradient decent to specify the metrics in task-specific learners. Thus the proposed model is able to handle unbalanced classes as well as to generate task-specific metrics. We test our approach in the `k-shot N-way' few-shot learning setting used in previous work and new realistic few-shot setting with diverse multi-domain tasks and flexible label numbers. Experiments show that our approach attains superior performances in both settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/04/2019

A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning

Few-shot learning aims to learn classifiers for new classes with only a ...
research
01/27/2021

Combat Data Shift in Few-shot Learning with Knowledge Graph

Many few-shot learning approaches have been designed under the meta-lear...
research
10/05/2019

Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning

Few-shot learning, which aims at extracting new concepts rapidly from ex...
research
02/12/2018

Few-Shot Learning with Metric-Agnostic Conditional Embeddings

Learning high quality class representations from few examples is a key p...
research
05/19/2018

Diverse Few-Shot Text Classification with Multiple Metrics

We study few-shot learning in natural language domains. Compared to many...
research
04/07/2022

Interval Bound Propagationx2013aided Fewx002dshot Learning

Few-shot learning aims to transfer the knowledge acquired from training ...
research
12/10/2020

Flexible Few-Shot Learning with Contextual Similarity

Existing approaches to few-shot learning deal with tasks that have persi...

Please sign up or login with your details

Forgot password? Click here to reset