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.

本文提出了 Few-Example Clustering (FEC) 算法，它使用对比学习对少量样本进行聚类，其步骤包括候选聚类分配的生成、对每个聚类分配进行对比学习和选择最佳候选，通过在 	extit {mini}-ImageNet 和 CUB-200-2011 数据集上进行实验证明，FEC 在各种情况下平均优于其他基线约 3.2％，并展现出逐渐上升、然后急剧下降的有趣学习曲线。