Online Clustering
25 papers with code • 0 benchmarks • 0 datasets
Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing the ground truth labels. Under the online scenario, data is in the form of streams, i.e., the whole dataset could not be accessed at the same time and the model should be able to make cluster assignments for new data without accessing the former data.
Image Credit: Online Clustering by Penalized Weighted GMM
Benchmarks
These leaderboards are used to track progress in Online Clustering
Latest papers
RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning
This result enables us to recast multi-agent communication into a novel online clustering problem over the local observations at each agent, with messages as cluster labels and the upper bound on the return gap as clustering loss.
Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
Agents build and use a local map to predict their observations; high surprisal leads to a "fragmentation event" that truncates the local map.
DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning
In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering.
Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation
We propose a method that does not require data augmentation, and that, differently from existing methods, regularizes the hard assignments.
CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
More importantly, the clustering algorithm conjointly operates on the features of both views, thereby elegantly bypassing the issue of content not represented in both views and the ambiguous matching of objects from one crop to the other.
Novel Class Discovery for 3D Point Cloud Semantic Segmentation
Firstly, we address the new problem of NCD for point cloud semantic segmentation.
Probabilistic Back-ends for Online Speaker Recognition and Clustering
This paper focuses on multi-enrollment speaker recognition which naturally occurs in the task of online speaker clustering, and studies the properties of different scoring back-ends in this scenario.
Online Arbitrary Shaped Clustering through Correlated Gaussian Functions
There is no convincing evidence that backpropagation is a biologically plausible mechanism, and further studies of alternative learning methods are needed.
Twin Contrastive Learning for Online Clustering
Specifically, we find that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster representation, respectively.
Federated Online Clustering of Bandits
Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems.