论文标题
无监督功能学习的渐进聚类净化
Progressive Cluster Purification for Unsupervised Feature Learning
论文作者
论文摘要
在无监督的特征学习中，基于样本特异性的方法忽略了类间信息，这会恶化表示模型的歧视能力。基于聚类的方法是错误的，可以探索由于每个群集中不可避免的类不一致的类别不一致的类别的完整类边界信息。在这项工作中，我们提出了一种基于聚类的新方法，该方法通过迭代地排除了渐进式群集形成期间的类样品不一致的样品，以一种简单的方式减轻噪声样本的影响。我们的方法（称为渐进群集纯化（PCP））通过逐渐减少训练过程中的簇数来实现渐进聚类，而簇的大小则随着模型表示能力的增长而不断扩展。使用精心设计的群集纯化机制，它通过过滤噪声样本来进一步纯化簇，从而通过利用精制簇作为伪标记，从而促进了随后的特征学习。对常用基准测试的实验表明，所提出的PCP改善了具有显着边缘的基线方法。我们的代码将在https://github.com/zhangyifei0115/pcp上找到。
In unsupervised feature learning, sample specificity based methods ignore the inter-class information, which deteriorates the discriminative capability of representation models. Clustering based methods are error-prone to explore the complete class boundary information due to the inevitable class inconsistent samples in each cluster. In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner. Our approach, referred to as Progressive Cluster Purification (PCP), implements progressive clustering by gradually reducing the number of clusters during training, while the sizes of clusters continuously expand consistently with the growth of model representation capability. With a well-designed cluster purification mechanism, it further purifies clusters by filtering noise samples which facilitate the subsequent feature learning by utilizing the refined clusters as pseudo-labels. Experiments on commonly used benchmarks demonstrate that the proposed PCP improves baseline method with significant margins. Our code will be available at https://github.com/zhangyifei0115/PCP.
