[论文解读] DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks

Dong Huang, Ding-Hua Chen+3 more|arXiv (Cornell University)|Jun 1, 2022

Domain Adaptation and Few-Shot Learning被引用 9

一句话总结

DeepCluE 提出了一种新颖的深度图像聚类框架，通过集成聚类方法利用多层特征表示来提升性能。通过使用实例级和聚类级对比学习进行权重共享的CNN训练，从多个网络层提取特征，并在二部图划分策略中应用基于熵的聚类加权方法，DeepCluE在六个图像数据集上实现了最先进（SOTA）的性能，优于现有的单层深度聚类方法。

ABSTRACT

Deep clustering has recently emerged as a promising technique for complex data clustering. Despite the considerable progress, previous deep clustering works mostly build or learn the final clustering by only utilizing a single layer of representation, e.g., by performing the K-means clustering on the last fully-connected layer or by associating some clustering loss to a specific layer, which neglect the possibilities of jointly leveraging multi-layer representations for enhancing the deep clustering performance. In view of this, this paper presents a Deep Clustering via Ensembles (DeepCluE) approach, which bridges the gap between deep clustering and ensemble clustering by harnessing the power of multiple layers in deep neural networks. In particular, we utilize a weight-sharing convolutional neural network as the backbone, which is trained with both the instance-level contrastive learning (via an instance projector) and the cluster-level contrastive learning (via a cluster projector) in an unsupervised manner. Thereafter, multiple layers of feature representations are extracted from the trained network, upon which the ensemble clustering process is further conducted. Specifically, a set of diversified base clusterings are generated from the multi-layer representations via a highly efficient clusterer. Then the reliability of clusters in multiple base clusterings is automatically estimated by exploiting an entropy-based criterion, based on which the set of base clusterings are re-formulated into a weighted-cluster bipartite graph. By partitioning this bipartite graph via transfer cut, the final consensus clustering can be obtained. Experimental results on six image datasets confirm the advantages of DeepCluE over the state-of-the-art deep clustering approaches.

研究动机与目标

• 为了解决现有深度聚类方法仅依赖单一网络层表示的局限性，该局限性可能遗漏网络深度间互补的语义信息。
• 通过在深度神经网络中联合利用多层的多样化特征，弥合深度聚类与集成聚类之间的差距。
• 通过在集成框架中引入基于熵的加权方案来建模聚类可靠性，从而提升聚类的鲁棒性和准确性。
• 开发一个统一的、端到端可训练的流程，集成对比学习、多层特征提取和共识聚类。

提出的方法

• 使用专用投影器，通过实例级和聚类级对比学习，对权重共享的卷积神经网络进行无监督训练。
• 从训练好的网络中提取多个网络层的特征表示，以捕捉不同抽象层级的层次化语义信息。
• 采用一种高效且高分化的U-SPEC算法，从多层特征中生成一组多样化的基本聚类。
• 基于熵的准则评估并为所有基本聚类中的聚类分配可靠性权重，以考虑聚类内和聚类间不确定性。
• 将加权聚类建模为加权聚类二部图，通过基于传输切割的划分方法获得共识聚类。
• 通过优化二部图以最大化一致性并尊重聚类可靠性评分，最终获得聚类结果。

实验结果

研究问题

• RQ1 能否通过联合利用深度神经网络中的多层表示，使图像聚类性能超越单层方法？
• RQ2 如何自动估计并利用多个基本聚类中的聚类可靠性以增强共识聚类？
• RQ3 在多层深度聚类框架中，集成规模和聚类加权对最终聚类质量有何影响？
• RQ4 同时引入实例级和聚类级对比学习是否能提升多层特征的聚类质量？

主要发现

• DeepCluE在六个基准图像数据集上实现了最先进性能，其NMI、ARI和ACC指标均持续优于现有深度聚类方法。
• 引入基于聚类的加权显著提升了聚类性能，消融实验表明在所有数据集上均取得一致增益。
• 增加集成规模（即基本聚类数量）可提升聚类质量，且在较高集成规模下性能趋于稳定。
• 消融实验确认，所提方法在加权聚类下优于使用均匀聚类权重的变体，在六个数据集上均表现更优。
• 该框架在多种图像数据上表现出鲁棒性和稳定性，涵盖小规模（Fashion、CIFAR）和大规模（Tiny-ImageNet、ImageNet）基准。