论文标题
基于聚类的对比度学习以改善面部表征
Clustering based Contrastive Learning for Improving Face Representations
论文作者
论文摘要
良好的聚类算法可以发现数据中的自然组。如果明智地使用这些分组，则为学习表征提供了一种薄弱的监督形式。在这项工作中，我们提出了基于聚类的对比学习（CCL），这是一种新的基于聚类的表示方法，它使用从聚类中获得的标签以及视频约束来学习判别性面部特征。我们展示了有关视频面群体学习表征的挑战性任务的方法。通过几项消融研究，我们分析了从不同来源创建成对正面和负面标签的影响。在三个具有挑战性的视频脸聚类数据集上进行的实验：BBT-0101，BF-0502和ACCIO表明，CCL在所有数据集上都实现了新的最新技术。
A good clustering algorithm can discover natural groupings in data. These groupings, if used wisely, provide a form of weak supervision for learning representations. In this work, we present Clustering-based Contrastive Learning (CCL), a new clustering-based representation learning approach that uses labels obtained from clustering along with video constraints to learn discriminative face features. We demonstrate our method on the challenging task of learning representations for video face clustering. Through several ablation studies, we analyze the impact of creating pair-wise positive and negative labels from different sources. Experiments on three challenging video face clustering datasets: BBT-0101, BF-0502, and ACCIO show that CCL achieves a new state-of-the-art on all datasets.
