AI Paper Atlas

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

Self-Supervised Learning with an Information Maximization Criterion

Serdar Ozsoy, Shadi Hamdan, Sercan O Arik, Deniz Yuret, Alper Tunga Erdogan

NeurIPS 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision

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
CorInfoMax vs best baseline on linear evaluationCorInfoMax · CIFAR-10top-1 accuracy (%): 92.94 -> 93.18Improved
CorInfoMax vs best baseline on linear evaluationCorInfoMax · CIFAR-100top-1 accuracy (%): 70.90 -> 71.61Improved
CorInfoMax vs best baseline on linear evaluationCorInfoMax · Tiny ImageNet (ResNet-50)top-1 accuracy (%): 49.86 -> 54.86Improved
CorInfoMax vs best baseline on linear evaluationCorInfoMax · ImageNet-100 (ResNet-50)top-1 accuracy (%): 81.6 -> 82.64Improved
CorInfoMax vs best baseline on linear evaluationCorInfoMax · ImageNet-1K (ResNet-50)top-1 accuracy (%): 69.3 -> 69.08No clear effect
CorInfoMax vs VICReg semi-supervised, 10% labelsCorInfoMax · ImageNet-1Ktop-1 accuracy (%): 62.16 -> 64.36Improved
CorInfoMax vs VICReg semi-supervised, 1% labelsCorInfoMax · ImageNet-1Ktop-1 accuracy (%): 44.75 -> 44.89No clear effect
lower attraction coefficient alpha from 1000 to 125 (ablation)CorInfoMax · CIFAR-100 (ResNet-18)top-1 accuracy (%): 71.61 -> 69.04Hurt
raise attraction coefficient alpha from 1000 to 2000 (ablation)CorInfoMax · CIFAR-100 (ResNet-18)top-1 accuracy (%): 71.61 -> 69.96Hurt
alpha 250 or 500 instead of 1000 (ablation)CorInfoMax · CIFAR-100 (ResNet-18)top-1 accuracy (%): 71.61 -> 71.19No clear effect
batch size 256 instead of 512 (ablation)CorInfoMax · CIFAR-100 (ResNet-18)top-1 accuracy (%): 71.61 -> 70.32Hurt
batch size 1024 instead of 512 (ablation)CorInfoMax · CIFAR-100 (ResNet-18)top-1 accuracy (%): 71.61 -> 69.98Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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