Deep Clustering
115 papers with code • 5 benchmarks • 2 datasets
Libraries
Use these libraries to find Deep Clustering models and implementationsLatest papers
SP$^2$OT: Semantic-Regularized Progressive Partial Optimal Transport for Imbalanced Clustering
To be more precise, we employ the strategy of majorization to reformulate the SP$^2$OT problem into a Progressive Partial Optimal Transport problem, which can be transformed into an unbalanced optimal transport problem with augmented constraints and can be solved efficiently by a fast matrix scaling algorithm.
Dataset Clustering for Improved Offline Policy Learning
Offline policy learning aims to discover decision-making policies from previously-collected datasets without additional online interactions with the environment.
Datacube segmentation via Deep Spectral Clustering
Extended Vision techniques are ubiquitous in physics.
Deep Clustering with Diffused Sampling and Hardness-aware Self-distillation
Deep clustering has gained significant attention due to its capability in learning clustering-friendly representations without labeled data.
Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype Aggregation
To tackle these critical issues, we present a novel end-to-end deep clustering framework with dynamic grouping and prototype aggregation, termed as DigPro.
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction
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.
P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering
Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches.
Deep Structure and Attention Aware Subspace Clustering
However, previous deep clustering methods, especially image clustering, focus on the features of the data itself and ignore the relationship between the data, which is crucial for clustering.
Contextually Affinitive Neighborhood Refinery for Deep Clustering
Previous endeavors in self-supervised learning have enlightened the research of deep clustering from an instance discrimination perspective.
Stable Cluster Discrimination for Deep Clustering
Meanwhile, one-stage methods are developed mainly for representation learning rather than clustering, where various constraints for cluster assignments are designed to avoid collapsing explicitly.