# Selecting task with optimal transport self-supervised learning for few-shot classification

arXiv: https://arxiv.org/abs/2204.00289 · HTML: https://mlsanity.com/paper/2204.00289/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 24 of 24)

- [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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Teacher-Student Curriculum Learning](https://mlsanity.com/paper/1707.00183/) (2017)
- [Task2Vec: Task Embedding for Meta-Learning](https://mlsanity.com/paper/1902.03545/) (2019)
- [Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation](https://mlsanity.com/paper/2001.08735/) (2020)
- [Optimal Transport for structured data with application on graphs](https://mlsanity.com/paper/1805.09114/) (2018)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks](https://mlsanity.com/paper/1802.03796/) (2018)
- [Graph Optimal Transport for Cross-Domain Alignment](https://mlsanity.com/paper/2006.14744/) (2020)
- [Cross-Domain Few-Shot Learning by Representation Fusion](https://mlsanity.com/paper/2010.06498/) (2020)
- [Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions](https://mlsanity.com/paper/1805.07594/) (2018)
- [Learning Embeddings into Entropic Wasserstein Spaces](https://mlsanity.com/paper/1905.03329/) (2019)
- [Representation Learning from Limited Educational Data with Crowdsourced Labels](https://mlsanity.com/paper/2009.11222/) (2020)
- [Privacy-preserving Stochastic Gradual Learning](https://mlsanity.com/paper/1810.00383/) (2018)

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

- [Wasserstein Task Embedding for Measuring Task Similarities](https://mlsanity.com/paper/2208.11726/) (2022)

## Abstract (arXiv)

Few-Shot classification aims at solving problems that only a few samples are available in the training process. Due to the lack of samples, researchers generally employ a set of training tasks from other domains to assist the target task, where the distribution between assistant tasks and the target task is usually different. To reduce the distribution gap, several lines of methods have been proposed, such as data augmentation and domain alignment. However, one common drawback of these algorithms is that they ignore the similarity task selection before training. The fundamental problem is to push the auxiliary tasks close to the target task. In this paper, we propose a novel task selecting algorithm, named Optimal Transport Task Selecting (OTTS), to construct a training set by selecting similar tasks for Few-Shot learning. Specifically, the OTTS measures the task similarity by calculating the optimal transport distance and completes the model training via a self-supervised strategy. By utilizing the selected tasks with OTTS, the training process of Few-Shot learning become more stable and effective. Other proposed methods including data augmentation and domain alignment can be used in the meantime with OTTS. We conduct extensive experiments on a variety of datasets, including MiniImageNet, CIFAR, CUB, Cars, and Places, to evaluate the effectiveness of OTTS. Experimental results validate that our OTTS outperforms the typical baselines, i.e., MAML, matchingnet, protonet, by a large margin (averagely 1.72% accuracy improvement).