论文标题
通过对比度学习很少示例聚类
Few-Example Clustering via Contrastive Learning
论文作者
论文摘要
我们提出了很少的示例聚类（FEC），这是一种新型算法，可以进行对比学习以群集以几个示例。我们的方法由以下三个步骤组成：（1）生成候选集群分配，（2）每个集群分配的对比度学习，以及（3）选择最佳候选者。基于以下假设：与其他人的对比学习者的训练速度要快，我们选择了在步骤（3）中学习早期训练损失最小的训练损失的候选人。在\ textit {mini} -imagenet和Cub-20011数据集上进行的广泛实验表明，在各种情况下，FEC平均比其他基本线平均优于其他基准。 FEC还表现出有趣的学习曲线，其中聚类性能逐渐增加，然后急剧下降。
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.
