# Few-Example Clustering via Contrastive Learning

arXiv: https://arxiv.org/abs/2207.04050 · HTML: https://mlsanity.com/paper/2207.04050/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 8 Jul 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [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)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [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)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning](https://mlsanity.com/paper/1905.06549/) (2019)
- [Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning](https://mlsanity.com/paper/1910.02224/) (2019)
- [TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification](https://mlsanity.com/paper/2003.06670/) (2020)
- [Differentiable Deep Clustering with Cluster Size Constraints](https://mlsanity.com/paper/1910.09036/) (2019)
- [Clustering based Contrastive Learning for Improving Face Representations](https://mlsanity.com/paper/2004.02195/) (2020)
- [Robust Training with Ensemble Consensus](https://mlsanity.com/paper/1910.09792/) (2019)
- [On perfect clustering of high dimension, low sample size data](https://mlsanity.com/paper/1612.09121/) (2016)
- [The classification for High-dimension low-sample size data](https://mlsanity.com/paper/2006.13018/) (2020)
- [Unsupervised Few-shot Learning via Self-supervised Training](https://mlsanity.com/paper/1912.12178/) (2019)
- [G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling](https://mlsanity.com/paper/2009.12007/) (2020)
- [Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time](https://mlsanity.com/paper/1902.08605/) (2019)

## Abstract (arXiv)

We propose Few-Example Clustering (FEC), a novel algorithm that performs contrastive learning to cluster few examples. Our method is composed of the following three steps: (1) generation of candidate cluster assignments, (2) contrastive learning for each cluster assignment, and (3) selection of the best candidate. Based on the hypothesis that the contrastive learner with the ground-truth cluster assignment is trained faster than the others, we choose the candidate with the smallest training loss in the early stage of learning in step (3). Extensive experiments on the textitmini-ImageNet and CUB-200-2011 datasets show that FEC outperforms other baselines by about 3.2% on average under various scenarios. FEC also exhibits an interesting learning curve where clustering performance gradually increases and then sharply drops.