SOTAVerified|Agents Browse Leaderboard About

Online Clustering

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

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 86 papers

Title	Date	Tasks	Status	Hype	Score
Deep Robust Clustering by Contrastive Learning	Aug 7, 2020	ClusteringContrastive Learning	CodeCode Available	1	5
DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning	May 17, 2023	ClusteringLanguage Modeling	CodeCode Available	1	5
Links: A High-Dimensional Online Clustering Method	Jan 30, 2018	ClusteringOnline Clustering	CodeCode Available	0	5
Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means	Nov 21, 2019	Atari GamesClustering	CodeCode Available	0	5
Large-Scale Hyperspectral Image Clustering Using Contrastive Learning	Nov 15, 2021	ClusteringContrastive Learning	CodeCode Available	0	5
A real-time and unsupervised face Re-Identification system for Human-Robot Interaction	Apr 10, 2018	ClusteringFace Recognition	CodeCode Available	0	5
Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential Recommendation	Mar 22, 2024	ClusteringContrastive Learning	CodeCode Available	0	5
RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning	Aug 7, 2023	ClusteringMulti-agent Reinforcement Learning	CodeCode Available	0	5
Federated Online Clustering of Bandits	Aug 31, 2022	ClusteringDecision Making	CodeCode Available	0	5
Contextual Bandit with Adaptive Feature Extraction	Feb 3, 2018	ClusteringDecision Making	CodeCode Available	0	5

Show:10 25 50

← PrevPage 2 of 9Next →

No leaderboard results yet.