Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

8-2020

Abstract

Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time by randomly sampling classes in meta-training data to construct fewshot tasks for episodic training. While a rich line of work focuses solely on how to extract meta-knowledge across tasks, we exploit the complementary problem on how to generate informative tasks. We argue that the randomly sampled tasks could be sub-optimal and uninformative (e.g., the task of classifying “dog” from “laptop” is often trivial) to the meta-learner. In this paper, we propose an adaptive task sampling method to improve the generalization performance. Unlike instance based sampling, task based sampling is much more challenging due to the implicit definition of the task in each episode. Therefore, we accordingly propose a greedy class-pair based sampling method, which selects difficult tasks according to class-pair potentials. We evaluate our adaptive task sampling method on two few-shot classification benchmarks, and it achieves consistent improvements across different feature backbones, meta-learning algorithms and datasets.

Keywords

Meta-learning, task sampling, few-shot learning

Discipline

Databases and Information Systems | Theory and Algorithms

Research Areas

Data Science and Engineering

Publication

Proceedings of the 16th European Conference on Computer Vision, Glasgow, UK, 2020, August 23 - 28

First Page

1

Last Page

17

ISBN

9783030586218

Publisher

Springer

City or Country

Virtual Event

Download

Share

COinS