AI Paper Atlas

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

ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs

Marah Halawa, Olaf Hellwich

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Contrastive versus non-contrastive theory · 0 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 ProtoFair regularizerSupCon · CelebA T:b,S:yEO: 16.9 -> 6.9Improved
add ProtoFair regularizerSupCon · CelebA T:a,S:mEO: 30.5 -> 14.2Improved
add ProtoFair regularizerSupCon · CelebA T:e,S:yEO: 10.8 -> 1.9Improved
add ProtoFair regularizerSupCon · CelebA T:a,S:yEO: 21.7 -> 17.7Improved
add ProtoFair regularizerSimCLR · CelebA T:a,S:m (no target labels)EO: 29.4 -> 21.9, ACC 75.7 -> 73.3Improved
add ProtoFair regularizerBarlowTwins · CelebA T:b,S:m (no target labels)EO: 12.07 -> 5.98Improved
add ProtoFair regularizerBYOL · CelebA T:e,S:m (no target labels)EO: 17.04 -> 7.11Improved
add ProtoFair regularizerSupCon · UTKFace alpha=4EO: 10.6 -> 6.6Improved
add ProtoFair regularizerSupCon · NIH Chest X-raysAUROC gap: 0.03 -> 0.01, AUROC 0.70 -> 0.72Improved
add ProtoFair regularizerSupCon · CelebA Bags Under Eyes sensitive probeprobe accuracy: 82.41 -> 76.07Improved
increase fairness weight lambda to 0.7 or higher (ablation)ProtoFair · CelebA (four T,S pairs)accuracyHurt
vary number of prototypes K (ablation)ProtoFair · CelebA (four T,S pairs)accuracy: accuracy within 83.0--84.5No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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