Deep image clustering methods are typically evaluated on small-scale balanced
classification datasets while feature-based $k$-means has been applied on
proprietary billion-scale datasets. In this work, we explore the performance of
feature-based deep clustering approaches on large-scale benchmarks whilst
disentangling the impact of the following data-related factors: i) class
imbalance, ii) class granularity, iii) easy-to-recognize classes, and iv) the
ability to capture multiple classes. Consequently, we develop multiple new
benchmarks based on ImageNet21K. Our experimental analysis reveals that
feature-based $k$-means is often unfairly evaluated on balanced datasets.
However, deep clustering methods outperform $k$-means across most large-scale
benchmarks. Interestingly, $k$-means underperforms on easy-to-classify
benchmarks by large margins. The performance gap, however, diminishes on the
highest data regimes such as ImageNet21K. Finally, we find that non-primary
cluster predictions capture meaningful classes (i.e. coarser classes).

在大规模基准数据集上，探索了基于特征的深度聚类方法的性能表现，并分析了数据相关因素对其影响，包括类别不平衡、类别粒度、易于识别的类别和捕获多类别的能力。通过基于 ImageNet21K 的多个新基准评估实验，发现基于特征的 $k$-means 在平衡数据集上评估不公平，而深度聚类方法在大多数大规模基准数据集上表现优于 $k$-means。有趣的是，$k$-means 在易于分类的基准上表现不佳，但在最高数据规模（如 ImageNet21K）上的性能差距减小。最后，发现非主要聚类预测能够捕获有意义的类别（即更粗略的类别）。

超越 ImageNet-1K 的深度聚类方法的扩展

Scaling Up Deep Clustering Methods Beyond ImageNet-1K

In this paper, we present a novel deep image clustering approach termed PICI,
which enforces the partial information discrimination and the cross-level
interaction in a joint learning framework. In particular, we leverage a
Transformer encoder as the backbone, through which the masked image modeling
with two paralleled augmented views is formulated. After deriving the class
tokens from the masked images by the Transformer encoder, three partial
information learning modules are further incorporated, including the PISD
module for training the auto-encoder via masked image reconstruction, the PICD
module for employing two levels of contrastive learning, and the CLI module for
mutual interaction between the instance-level and cluster-level subspaces.
Extensive experiments have been conducted on six real-world image datasets,
which demononstrate the superior clustering performance of the proposed PICI
approach over the state-of-the-art deep clustering approaches. The source code
is available at this https URL

本文介绍了一种名为 PICI 的新型深度图像聚类方法，通过部分信息辨别和跨层级交互在联合学习框架中进行。通过使用 Transformer 编码器作为骨干网络，我们形成了具有两个并行增广视图的蒙版图像建模。从通过 Transformer 编码器从蒙版图像中导出的类别标记开始，我们进一步融入了三个部分信息学习模块，包括通过蒙版图像重构训练自动编码器的 PISD 模块、使用两个层次的对比学习的 PICD 模块，以及相互交互的实例级和群集级子空间之间的 CLI 模块。我们在六个真实世界的图像数据集上进行了大量实验，结果表明所提出的 PICI 方法在深度聚类方法方面具有优越的聚类性能。源代码可在此 https URL 找到。