AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Deep Clustering: On the Link Between Discriminative Models and K-Means

Mohammed Jabi, Marco Pedersoli, Amar Mitiche, Ismail Ben Ayed

TPAMI 2019 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 129 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace direct mutual information maximization (MI-D) by ADM (MI-ADM) (ablation)mutual information clustering · FRGC clusteringACC: 0.322 -> 0.431Improved
replace direct mutual information maximization (MI-D) by ADM (MI-ADM) (ablation)mutual information clustering · CMU-PIE clusteringACC: 0.705 -> 0.858Improved
replace direct mutual information maximization (MI-D) by ADM (MI-ADM) (ablation)mutual information clustering · MNIST-full clusteringACC: 0.967 -> 0.969No clear effect
replace direct mutual information maximization (MI-D) by ADM (MI-ADM) (ablation)mutual information clustering · USPS clusteringACC: 0.979 -> 0.979No clear effect
replace direct mutual information maximization (MI-D) by ADM (MI-ADM) (ablation)mutual information clustering · YTF clusteringACC: 0.616 -> 0.606Mixed
use discriminative MI-ADM instead of generative SR-K-meansclustering · MNIST-full clusteringACC: 0.939 -> 0.969Improved
use discriminative MI-ADM instead of generative SR-K-meansclustering · FRGC clusteringNMI: 0.487 -> 0.580Improved
use MI-ADM instead of SR-K-means on unbalanced dataclustering · YTF clusteringACC: 0.605 -> 0.606No clear effect
use MI-ADM versus DEPICTclustering · MNIST-full clusteringACC: 0.971 -> 0.969No clear effect
add entropy term H(Q) to the objective (ablation)MI-ADM · six clustering datasetsACCNo clear effect
use regularized soft K-means instead of DCN hard K-meansSR-K-means · MNIST-full clusteringACC: 0.83 -> 0.939Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy