AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Generalised Mutual Information for Discriminative Clustering

Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron, Warith HARCHAOUI, Mickaël Leclercq, Arnaud Droit, Frederic Precioso

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 2 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 KL mutual information with MMD OvADiscriminative clustering on a Gaussian and Student-t mixture · Gaussian and Student-t mixtureARI: 0 -> 0.922Improved
Use MMD OvO instead of MMD OvA (ablation)GEMINI with an MLP · Gaussian and Student-t mixtureARI: 0.922 -> 0.921No clear effect
Use Wasserstein OvO instead of Wasserstein OvA (ablation)GEMINI with an MLP · Gaussian and Student-t mixtureARI: 0.915 -> 0.922No clear effect
Replace KL mutual information with Wasserstein OvADiscriminative clustering · MNIST, 10 clusters, MLPARI: 0.320 -> 0.471Improved
Replace KL mutual information with Wasserstein OvADiscriminative clustering · MNIST, 10 clusters, LeNet-5ARI: 0.138 -> 0.463Improved
Replace KL mutual information with Wasserstein OvODiscriminative clustering · MNIST, 15 clusters, MLPARI: 0.271 -> 0.415Improved
Replace KL mutual information with Wasserstein OvADiscriminative clustering · MNIST, 15 clusters, LeNet-5ARI: 0.136 -> 0.446Improved
Change backbone from MLP to LeNet-5 (ablation)KL OvA GEMINI · MNIST, 10 clustersARI: 0.320 -> 0.138Hurt
Replace linear kernel with a pretrained SIMCLR kernel (ablation)MMD OvA GEMINI with LeNet-5 · CIFAR10ARI: 0.049 -> 0.157Improved
Replace Euclidean image distance with SIMCLR feature distance (ablation)Wasserstein OvA GEMINI with LeNet-5 · CIFAR10ARI: 0.043 -> 0.079Improved
Replace linear kernel with a pretrained SIMCLR kernel (ablation)MMD OvO GEMINI with ResNet-18 · CIFAR10ARI: 0.044 -> 0.145Improved
Replace Euclidean image distance with SIMCLR feature distance (ablation)Wasserstein OvA GEMINI with ResNet-18 · CIFAR10ARI: 0.037 -> 0.052Improved

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