Few-Example Clustering via Contrastive Learning
This addresses the challenge of clustering with limited data for machine learning applications, representing an incremental advancement in the field.
The paper tackles the problem of clustering few examples by proposing Few-Example Clustering (FEC), which uses contrastive learning and candidate selection, resulting in an average performance improvement of about 3.2% over baselines on datasets like mini-ImageNet and CUB-200-2011.
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.