# Trainable Class Prototypes for Few-Shot Learning

arXiv: https://arxiv.org/abs/2106.10846 · HTML: https://mlsanity.com/paper/2106.10846/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 34 references that are in the map.
- First posted on arXiv 21 Jun 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [Edge-labeling Graph Neural Network for Few-shot Learning](https://mlsanity.com/paper/1905.01436/) (2019)
- [Online Deep Clustering for Unsupervised Representation Learning](https://mlsanity.com/paper/2006.10645/) (2020)
- [Unsupervised Learning via Meta-Learning](https://mlsanity.com/paper/1810.02334/) (2018)
- [Unsupervised Meta-Learning For Few-Shot Image Classification](https://mlsanity.com/paper/1811.11819/) (2018)
- [Dense Classification and Implanting for Few-Shot Learning](https://mlsanity.com/paper/1903.05050/) (2019)
- [LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning](https://mlsanity.com/paper/1905.06331/) (2019)
- [Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation](https://mlsanity.com/paper/1902.09884/) (2019)
- [Unsupervised Few-shot Learning via Self-supervised Training](https://mlsanity.com/paper/1912.12178/) (2019)
- [Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification](https://mlsanity.com/paper/2001.09849/) (2020)
- [Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation](https://mlsanity.com/paper/2004.05805/) (2020)

## Built on by (most cited first, 1 of 1)

- [BECLR: Batch Enhanced Contrastive Few-Shot Learning](https://mlsanity.com/paper/2402.02444/) (2024)

## Abstract (arXiv)

Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the artificial ones within the meta-training and task-training framework. Also to avoid the disadvantages that the episodic meta-training brought, we adopt non-episodic meta-training based on self-supervised learning. Overall we solve the few-shot tasks in two phases: meta-training a transferable feature extractor via self-supervised learning and training the prototypes for metric classification. In addition, the simple attention mechanism is used in both meta-training and task-training. Our method achieves state-of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification dataset, with about 20% increase compared to the available unsupervised few-shot learning methods.