# Meta-Learned Confidence for Few-shot Learning

arXiv: https://arxiv.org/abs/2002.12017 · HTML: https://mlsanity.com/paper/2002.12017/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning](https://mlsanity.com/paper/2110.09446/) (2021)
- [MetaDelta: A Meta-Learning System for Few-shot Image Classification](https://mlsanity.com/paper/2102.10744/) (2021)
- [Sill-Net: Feature Augmentation with Separated Illumination Representation](https://mlsanity.com/paper/2102.03539/) (2021)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning](https://mlsanity.com/paper/2110.09374/) (2021)
- [Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy](https://mlsanity.com/paper/2111.04331/) (2021)
- [Multi-Level Contrastive Learning for Few-Shot Problems](https://mlsanity.com/paper/2107.07608/) (2021)
- [Uncertainty-based Network for Few-shot Image Classification](https://mlsanity.com/paper/2205.08157/) (2022)
- [Class-Specific Channel Attention for Few-Shot Learning](https://mlsanity.com/paper/2209.01332/) (2022)

## Abstract (arXiv)

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.