AI Paper Atlas

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

Learning Disentangled Representations via Mutual Information Estimation

Eduardo Hugo Sanchez, Mathieu Serrurier, Mathias Ortner

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 103 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
switch the shared representations (SSR) (ablation)shared representation learning · Colored-MNIST (S_X)distance to ideal: 1.0209 -> 0.0563Improved
add the L1 distance between S_X and S_Y (ablation)shared representation learning · Colored-MNIST (S_X)distance to ideal: 0.0780 -> 0.0563Improved
add the global mutual information term (ablation)shared representation learning · Colored-MNIST (S_X)distance to ideal: 0.0795 -> 0.0563Improved
add the local mutual information term (ablation)shared representation learning · Colored-MNIST (S_X)distance to ideal: 0.1958 -> 0.0563Improved
switch the shared representations (SSR) (ablation)shared representation learning · IAM (S_X)distance to ideal: 0.6094 -> 0.4730Improved
add the L1 distance between S_X and S_Y (ablation)shared representation learning · IAM (S_X)distance to ideal: 0.5412 -> 0.4730Improved
add the global mutual information term (ablation)shared representation learning · IAM (S_X)distance to ideal: 0.4886 -> 0.4730Improved
add the local mutual information term (ablation)shared representation learning · IAM (S_X)distance to ideal: 0.6235 -> 0.4730Improved
increase adversarial weight lambda_adv from 0.0 to 0.025 (ablation)exclusive representation · colored-MNIST / 3D Shapesexclusive-representation leakage of shared attributes: 0.0 -> 0.025Improved
increase adversarial weight lambda_adv beyond 0.025 (to 0.05) (ablation)exclusive representation · colored-MNIST / 3D Shapesexclusive attribute classification accuracy: 0.025 -> 0.05Hurt
use mutual-information model instead of VAE-GAN of Gonzalez-Garcia et al.disentangled representation · Colored-MNIST (background color)distance to ideal: 0.9581 -> 0.0563Improved
use mutual-information model instead of VAE-GAN of Gonzalez-Garcia et al.disentangled representation · 3D Shapesdistance to ideal: 2.6643 -> 0.0020Improved

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