# One-shot Learning with Absolute Generalization

arXiv: https://arxiv.org/abs/2105.13559 · HTML: https://mlsanity.com/paper/2105.13559/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 28 May 2021.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Infinite Mixture Prototypes for Few-Shot Learning](https://mlsanity.com/paper/1902.04552/) (2019)
- [Laplacian Regularized Few-Shot Learning](https://mlsanity.com/paper/2006.15486/) (2020)
- [Few-Shot Learning Through an Information Retrieval Lens](https://mlsanity.com/paper/1707.02610/) (2017)
- [Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data](https://mlsanity.com/paper/1807.10916/) (2018)

## Abstract (arXiv)

One-shot learning is proposed to make a pretrained classifier workable on a new dataset based on one labeled samples from each pattern. However, few of researchers consider whether the dataset itself supports one-shot learning. In this paper, we propose a set of definitions to explain what kind of datasets can support one-shot learning and propose the concept "absolute generalization". Based on these definitions, we proposed a method to build an absolutely generalizable classifier. The proposed method concatenates two samples as a new single sample, and converts a classification problem to an identity identification problem or a similarity metric problem. Experiments demonstrate that the proposed method is superior to baseline on one-shot learning datasets and artificial datasets.