AI Paper Atlas

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

$i$-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee

ICLR 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Empirical contrastive visual learning · 52 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
Add i-Mix to N-pairN-pair contrastive learning · CIFAR-10accuracy: 93.3 -> 95.6Improved
Add i-Mix to MoCo v2MoCo v2 · CIFAR-100accuracy: 71.6 -> 78.1Improved
Add i-Mix to BYOLBYOL · Speech Commandsaccuracy: 94.8 -> 98.3Improved
Add i-Mix to MoCo v2MoCo v2 · CovTypeaccuracy: 70.5 -> 73.1Improved
Add i-Mix with no other augmentations (ablation)MoCo v2 · CIFAR-10accuracy: 47.7 -> 83.4Improved
Add i-Mix with no other augmentations (ablation)MoCo v2 · Speech Commandsaccuracy: 76.9 -> 92.8Improved
Add i-Mix with no other augmentations (ablation)MoCo v2 · Higgs1Maccuracy: 65.5 -> 72.9Improved
Add InputMix alongside i-Mix (ablation)i-Mix on CIFAR-10 without other data augmentations · CIFAR-10accuracy: 75.1% to 83.4%Improved
Use i-CutMix instead of i-MixUp (ablation)N-pair and SimCLR · CIFAR-100 pretext to CIFAR-10 downstreamaccuracy: 86.2 vs. 85.1; 85.2 vs. 83.7Mixed
Use i-CutMix instead of i-MixUp (ablation)N-pair and SimCLR · CIFAR-10 pretext to CIFAR-100 downstreamaccuracy: 63.3 vs. 61.5; 61.4 vs. 57.1Mixed
Apply i-Mix to supervised contrastive learning (ablation)N-pair supervised contrastive learning · CIFAR-10accuracy: 95.7% to 97.0%Improved
Apply i-Mix to supervised contrastive learning with CIFAR-10 pretext (ablation)N-pair supervised contrastive learning · CIFAR-100 downstreamaccuracy: 58.9 to 57.8Hurt

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