AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Learning about an exponential amount of conditional distributions

Mohamed Belghazi, Maxime Oquab, David Lopez-Paz

NeurIPS 2019 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 12 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
use adversarial training instead of moment matching (ablation)NC · 3D Gaussian, a=(1, 0, 0), r=(0, 1, 1)conditional parameter error: 0.67 -> 0.13Improved
condition both the discriminator and NC on available and requested masks (ablation)NC · 3D GaussianEuclidean parameter error: 0.12 -> 0.07Improved
remove mask conditioning from the discriminator while retaining it in NC (ablation)NC · 3D GaussianEuclidean parameter error: 0.07 -> 0.17Hurt
remove mask conditioning from NC while retaining it in the discriminator (ablation)NC · 3D GaussianEuclidean parameter error: 0.07 -> 0.15Hurt
use NC features rather than the strongest listed baseline featuresSVHN classification with linear SVM · SVHN testtest error: 16.61 vs 17.12Mixed
use NC features rather than VAEAC featuresCelebA attribute classification · CelebA testbalanced accuracy (mean): 66.06 -> 82.21Improved

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