AI Paper Atlas

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

InfoNCE Induces Gaussian Distribution

Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 8 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
train with InfoNCE instead of cross-entropy supervision (ablation)ResNet-18 · CIFAR-10CV of norms: 0.5 -> 0.09Improved
train with InfoNCE instead of cross-entropy supervision (ablation)ResNet-18 · CIFAR-10AD average statistic: 3.3 -> 0.43Improved
train with InfoNCE instead of cross-entropy supervision (ablation)ResNet-18 · CIFAR-10DP fraction of normal features: 3.9% -> 94.5%Improved
train the linear encoder longer, from epoch 0 to epoch 100 (ablation)linear InfoNCE encoder · Synthetic binaryCV of norms: 0.36 -> 0.09Improved
train the linear encoder longer, from epoch 0 to epoch 100 (ablation)linear InfoNCE encoder · Synthetic binaryAD fraction of normal features: 30% -> 97%Improved
train the linear encoder longer, from epoch 0 to epoch 100 (ablation)linear InfoNCE encoder · Synthetic binaryDP fraction of normal features: 15% -> 98%Improved
use a self-supervised pretrained model instead of supervised ResNet-34 (ablation)pretrained encoders · MS-COCOAD fraction of normal features: 0.0% -> 97.0%Improved
use a self-supervised pretrained model instead of supervised DenseNet (ablation)pretrained encoders · MS-COCOAD fraction of normal features: 42.2% -> 97.0%Improved
increase batch size and dimension (ablation)linear InfoNCE encoder · Synthetic LaplaceCV of normsImproved
increase batch size or dimension (ablation)linear InfoNCE encoder · Synthetic datauniformityImproved
apply post hoc whitening to representations (ablation)CLIP and DINO · pretrained embeddingsuniformityImproved
train longer on CIFAR-10 (ablation)two-layer MLP InfoNCE · CIFAR-10fraction of coordinates passing DP testImproved

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