AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score

Xuanning Zhou, Zihao Shi, Hao Zeng, Xiaobo Xia, Bingyi Jing, Hongxin Wei

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 5 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 unlabeled data with NNM scores to calibration (SemiCP)split CP, ResNet50 · CIFAR-10 (10 labeled)coverage gap: 6.4 -> 1.1Improved
add SemiCP to group-conditional CPgroup-conditional split CP · CIFAR-100 (n_avg=10)coverage gap: 6.50 -> 4.75Improved
add SemiCP to InterpolationInterpolation CP · CIFAR-100 (10 labeled)coverage gap: 9 -> 3.9Improved
add SemiCP to ClusterCPClusterCP · CIFAR-100 (group-conditional)coverage gap and set sizeImproved
use Interpolation alone instead of Standardsplit CP · CIFAR-100coverage gapHurt
increase number of unlabeled examples (ablation)SemiCP · ImageNet (50 labeled)coverage gap and set sizeImproved
add SemiCP with only 10 unlabeled examples (ablation)split CP · ImageNet (50 labeled)coverage gap: about 0.1 gap reductionImproved
add SemiCP across 10 architecturessplit CP · ImageNet (50 labeled, 20000 unlabeled)coverage gap: 3.3 -> 2.1Improved

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