P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering
This addresses a practical limitation in deep clustering methods that assume uniform class distributions, making them more applicable to real-world imbalanced data.
The paper tackles deep clustering with imbalanced class distributions by proposing a pseudo-labeling framework that formulates label generation as a progressive partial optimal transport problem, achieving state-of-the-art results on datasets like long-tailed CIFAR100, ImageNet-R, and iNaturalist2018.
Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant progress in recent years, most existing methods focus on uniformly distributed datasets, significantly limiting the practical applicability of their methods. In this paper, we first introduce a more practical problem setting named deep imbalanced clustering, where the underlying classes exhibit an imbalance distribution. To tackle this problem, we propose a novel pseudo-labeling-based learning framework. Our framework formulates pseudo-label generation as a progressive partial optimal transport problem, which progressively transports each sample to imbalanced clusters under prior distribution constraints, thus generating imbalance-aware pseudo-labels and learning from high-confident samples. In addition, we transform the initial formulation into an unbalanced optimal transport problem with augmented constraints, which can be solved efficiently by a fast matrix scaling algorithm. Experiments on various datasets, including a human-curated long-tailed CIFAR100, challenging ImageNet-R, and large-scale subsets of fine-grained iNaturalist2018 datasets, demonstrate the superiority of our method.