ReMP: Rectified Metric Propagation for Few-Shot Learning
arXiv:2012.00904
Abstract
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.
arXiv commentTech Report, 11 pages
References in corpus (10)
- Prototypical Networks for Few-shot Learning
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- Meta-Learning with Implicit Gradients
- Meta-Learning with Latent Embedding Optimization
- Cross Attention Network for Few-shot Classification
- How to train your MAML
- Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
- Meta-Learned Confidence for Few-shot Learning
- MetaFun: Meta-Learning with Iterative Functional Updates