# Few-Example Clustering via Contrastive Learning

Source: [Few-Example Clustering via Contrastive Learning](<https://www.sota2.com/research/paper/68fa6cf51e209131cea36d4a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:54.249Z

Authors: Minguk Jang, Sae-Young Chung

Published: 2022-07-08T05:33:46.000Z

## Abstract

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 \\textit{mini}-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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.04050>)

[PDF](<https://arxiv.org/pdf/2207.04050.pdf>)