ReMP: Rectified Metric Propagation for Few-Shot Learning

by   fcq, et al.

Few-shot learning features the capability of generalizing from a few examples. In this paper, we first identify that a discriminative feature space, namely a rectified metric space, that is learned to maintain the metric consistency from training to testing, is an essential component to the success of metric-based few-shot learning. Numerous analyses indicate that a simple modification of the objective can yield substantial performance gains. The resulting approach, called rectified metric propagation (ReMP), further optimizes an attentive prototype propagation network, and applies a repulsive force to make confident predictions. Extensive experiments demonstrate that the proposed ReMP is effective and efficient, and outperforms the state of the arts on various standard few-shot learning datasets.


page 7

page 8


TADAM: Task dependent adaptive metric for improved few-shot learning

Few-shot learning has become essential for producing models that general...

One-shot Learning with Absolute Generalization

One-shot learning is proposed to make a pretrained classifier workable o...

Discriminative Few-Shot Learning Based on Directional Statistics

Metric-based few-shot learning methods try to overcome the difficulty du...

Transductive Propagation Network for Few-shot Learning

Few-shot learning aims to build a learner that quickly generalizes to no...

Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning

Few-Shot Learning (FSL) aims to improve a model's generalization capabil...

Few-shot Learning for Slot Tagging with Attentive Relational Network

Metric-based learning is a well-known family of methods for few-shot lea...

Wandering Within a World: Online Contextualized Few-Shot Learning

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