We present a general methodology that learns to classify images without labels by leveraging pretrained feature extractors. Our approach involves self-distillation training of clustering heads, based on the fact that nearest neighbors in the pretrained feature space are likely to share the same label. We propose a novel objective to learn associations between images by introducing a variant of pointwise mutual information together with instance weighting. We demonstrate that the proposed objective is able to attenuate the effect of false positive pairs while efficiently exploiting the structure in the pretrained feature space. As a result, we improve the clustering accuracy over $k$-means on $17$ different pretrained models by $6.1$\% and $12.2$\% on ImageNet and CIFAR100, respectively. Finally, using self-supervised pretrained vision transformers we push the clustering accuracy on ImageNet to $61.6$\%. The code will be open-sourced.

本篇论文讲述了一种基于预训练特征提取器，通过自蒸馏训练聚类头来学习无标签图像分类的通用方法，并介绍了一种新的目标函数，利用一种变体的点间互信息和实例加权来学习图像之间的关联，以提高聚类准确性。最终使用自监督预训练视觉Transformer推进了在ImageNet上的聚类精度达到61.6％。

使用预先训练模型探索深层图像聚类的极限