Memory-Augmented Relation Network for Few-Shot Learning

by   Jun He, et al.

Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision of limited number of labelled instances. However, most of them treat each individual instance in the working context separately without considering its relationships with the others. In this work, we investigate a new metric-learning method, Memory-Augmented Relation Network (MRN), to explicitly exploit these relationships. In particular, for an instance, we choose the samples that are visually similar from the working context, and perform weighted information propagation to attentively aggregate helpful information from the chosen ones to enhance its representation. In MRN, we also formulate the distance metric as a learnable relation module which learns to compare for similarity measurement, and augment the working context with memory slots, both contributing to its generality. We empirically demonstrate that MRN yields significant improvement over its ancestor and achieves competitive or even better performance when compared with other few-shot learning approaches on the two major benchmark datasets, i.e. miniImagenet and tieredImagenet.


page 1

page 4

page 7

page 8


Revisiting Metric Learning for Few-Shot Image Classification

The goal of few-shot learning is to recognize new visual concepts with j...

Deep Comparison: Relation Columns for Few-Shot Learning

Few-shot deep learning is a topical challenge area for scaling visual re...

ATRM: Attention-based Task-level Relation Module for GNN-based Few-shot Learning

Recently, graph neural networks (GNNs) have shown powerful ability to ha...

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning

Few-shot learning is a fundamental and challenging problem since it requ...

ReMP: Rectified Metric Propagation for Few-Shot Learning

Few-shot learning features the capability of generalizing from a few exa...

Memory-Based Neighbourhood Embedding for Visual Recognition

Learning discriminative image feature embeddings is of great importance ...

Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective

Few-shot learning problem focuses on recognizing unseen classes given a ...

Please sign up or login with your details

Forgot password? Click here to reset