Online Clustering

12 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

Most implemented papers

AN ONLINE ALGORITHM FOR CONSTRAINED FACE CLUSTERING IN VIDEOS

ankuPRK/COFC International Conference on Image Processing (ICIP) 2018

We address the problem of face clustering in long, real world videos. This is a challenging task because faces in such videos exhibit wid evariability in scale, pose, illumination, expressions, and may also be partially occluded.

Links: A High-Dimensional Online Clustering Method

QEDan/links_clustering 30 Jan 2018

We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space.

Contextual Bandit with Adaptive Feature Extraction

doerlbh/ABaCoDE 3 Feb 2018

Our experiments on a variety of datasets, and both in stationary and non-stationary environments of several kinds demonstrate clear advantages of the proposed adaptive representation learning over the standard contextual bandit based on "raw" input contexts.

A real-time and unsupervised face Re-Identification system for Human-Robot Interaction

ibug-group/face_reid 10 Apr 2018

In this paper, we present an effective and unsupervised face Re-ID system which simultaneously re-identifies multiple faces for HRI.

Unsupervised Progressive Learning and the STAM Architecture

CameronTaylorFL/stam 3 Apr 2019

We first pose the Unsupervised Progressive Learning (UPL) problem: an online representation learning problem in which the learner observes a non-stationary and unlabeled data stream, learning a growing number of features that persist over time even though the data is not stored or replayed.

Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means

Kaixhin/EC 21 Nov 2019

Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches.

Contrastive Clustering

Yunfan-Li/Contrastive-Clustering 21 Sep 2020

In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning.

Group-aware Label Transfer for Domain Adaptive Person Re-identification

zkcys001/UDAStrongBaseline CVPR 2021

In this paper, we propose a Group-aware Label Transfer (GLT) algorithm, which enables the online interaction and mutual promotion of pseudo-label prediction and representation learning.

Unsupervised Visual Representation Learning by Online Constrained K-Means

idstcv/coke CVPR 2022

Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination.

Large-Scale Hyperspectral Image Clustering Using Contrastive Learning

angrycai/sscc 15 Nov 2021

Specifically, we exploit a symmetric twin neural network comprised of a projection head with a dimensionality of the cluster number to conduct dual contrastive learning from a spectral-spatial augmentation pool.