Boosting Few-Shot Learning With Adaptive Margin Loss

05/28/2020
by   Aoxue Li, et al.
5

Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve the generalization ability of metric-based meta-learning approaches for few-shot learning problems. Specifically, we first develop a class-relevant additive margin loss, where semantic similarity between each pair of classes is considered to separate samples in the feature embedding space from similar classes. Further, we incorporate the semantic context among all classes in a sampled training task and develop a task-relevant additive margin loss to better distinguish samples from different classes. Our adaptive margin method can be easily extended to a more realistic generalized FSL setting. Extensive experiments demonstrate that the proposed method can boost the performance of current metric-based meta-learning approaches, under both the standard FSL and generalized FSL 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
07/08/2018

Large Margin Few-Shot Learning

The key issue of few-shot learning is learning to generalize. In this pa...
research
06/10/2019

Few-Shot Learning with Per-Sample Rich Supervision

Learning with few samples is a major challenge for parameter-rich models...
research
05/27/2023

Instance-based Max-margin for Practical Few-shot Recognition

In order to mimic the human few-shot learning (FSL) ability better and t...
research
10/12/2022

Semantic Cross Attention for Few-shot Learning

Few-shot learning (FSL) has attracted considerable attention recently. A...
research
04/01/2020

Learning to Select Base Classes for Few-shot Classification

Few-shot learning has attracted intensive research attention in recent y...
research
01/09/2022

Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples

Over the last couple of years few-shot learning (FSL) has attracted grea...

Please sign up or login with your details

Forgot password? Click here to reset