AI Paper Atlas

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

Interventional Contrastive Learning with Meta Semantic Regularizer

Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Bing Su, Hui Xiong

ICML 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Inductive bias and minimal representations · 10 citations (OpenAlex)

Read the paper

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 MSR to LMCLLMCL · CIFAR-10linear accuracy: 91.91 -> 92.45Improved
Add MSR to BYOLBYOL · CIFAR-105-nn accuracy: 89.45 -> 90.12Improved
Add MSR to BYOLBYOL · CIFAR-100linear accuracy: 66.60 -> 66.97Improved
Add MSR to BYOLBYOL · STL-10linear accuracy: 91.99 -> 93.22Improved
Add MSR to BYOLBYOL · Tiny ImageNet5-nn accuracy: 36.24 -> 37.54Improved
Add MSR to ReSSLReSSL · CIFAR-100linear accuracy: 63.79 -> 65.12Hurt
Add MSR to SimCLRSimCLR · ImageNet-100top-1 accuracy: 70.15 -> 72.08Improved
Add MSR to SimCLRSimCLR · ImageNettop-1 accuracy: 69.3 -> 70.9Improved
Add MSR to BYOLBYOL · ImageNettop-1 accuracy: 74.3 -> 75.4Improved
Add MSR to BYOLBYOL · ImageNet 1% labelstop-1 accuracy: 53.2 -> 55.5Improved
Add MSR to BYOLBYOL · ImageNet 10% labelstop-5 accuracy: 89.0 -> 90.7Improved
Set gamma to 1 for uniformity loss (ablation)ICL-MSR (SimCLR) · CIFAR-10accuracyImproved

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