AI Paper Atlas

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

Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning

Lin-Han Jia, Siyu Han, Wen-Chao Hu, Jie-Jing Shao, Wen-Da Wei, Zhi Zhou, Lan-Zhe Guo, Yu-Feng Li

ICML 2026 · 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
add reliability estimate to learnability alone (ablation)Performance estimator · CIFAR-10 self-supervisedPearson correlation: 0.224 -> 0.716Improved
add completeness estimate to learnability alone (ablation)Performance estimator · CIFAR-10 self-supervisedPearson correlation: 0.224 -> 0.746Improved
add learnability to reliability + completeness (ablation)Performance estimator · CIFAR-10 self-supervisedPearson correlation: 0.808 -> 0.820Improved
add learnability to reliability + completeness (ablation)Performance estimator · CIFAR-10 semi-supervisedPearson correlation: 0.773 -> 0.785Improved
use all three indicators instead of any single one (ablation)Performance estimator · CIFAR-10 semi-supervisedPearson correlation: 0.692 -> 0.785Improved
increase unlabeled estimation data from 10x to 50x the labeled data (ablation)Performance estimator · CIFAR-10 self-supervisedPearson correlation: 0.820 -> 0.854Improved
increase unlabeled estimation data from 10x to 50x the labeled data (ablation)Performance estimator · CIFAR-10 semi-supervisedPearson correlation: 0.785 -> 0.803Improved
train longer (10 epochs instead of 5) (ablation)Performance estimator · CIFAR-10 semi-supervisedPearson correlation: 0.785 -> 0.874Improved
lower learning rate to 1e-5 (ablation)Performance estimator · CIFAR-10 semi-supervisedPearson correlation: 0.785 -> 0.666Hurt
swap ViT-B backbone for ResNet-50 (ablation)Performance estimator · CIFAR-10 semi-supervisedPearson correlation: 0.785 -> 0.478Hurt
use estimator instead of full training and validationPretext task assessment · CIFAR-10time (s): 1651.6 -> 29.6Improved
use contrastive/semi-supervised algorithm-specific training (e.g. MoCo) instead of the basic unified algorithm (ablation)Performance estimator · CIFAR-10 self-supervisedPearson correlation: 0.820 -> 0.453Hurt

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