Meta-Learned Confidence for Few-shot Learning

Abstract

Transductive inference is an effective means of tackling the data deficiency problem in few-shot learning settings. A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples, or confidence-weighted average of all the query samples. However, a caveat here is that the model confidence may be unreliable, which may lead to incorrect predictions. To tackle this issue, we propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries such that they improve the model's transductive inference performance on unseen tasks. We achieve this by meta-learning an input-adaptive distance metric over a task distribution under various model and data perturbations, which will enforce consistency on the model predictions under diverse uncertainties for unseen tasks. Moreover, we additionally suggest a regularization which explicitly enforces the consistency on the predictions across the different dimensions of a high-dimensional embedding vector. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets, on which it largely outperforms strong recent baselines and obtains new state-of-the-art results. Further application on semi-supervised few-shot learning tasks also yields significant performance improvements over the baselines. The source code of our algorithm is available at https://github.com/seongmin-kye/MCT.

References in corpus (18)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• On Calibration of Modern Neural Networks
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Theoretical Models of Learning to Learn
• Matching Networks for One Shot Learning
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• Learning to Self-Train for Semi-Supervised Few-Shot Classification
• Fast Context Adaptation via Meta-Learning
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• Cross Attention Network for Few-shot Classification
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• Dynamic Few-Shot Visual Learning without Forgetting
• Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
• DPGN: Distribution Propagation Graph Network for Few-shot Learning

Cited by in corpus (7)

• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
• Data Augmentation for Meta-Learning
• Sill-Net: Feature Augmentation with Separated Illumination Representation
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
• MetaDelta: A Meta-Learning System for Few-shot Image Classification
• ReMP: Rectified Metric Propagation for Few-Shot Learning
• A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning