AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning

Jiahe Chen, Qian Shao, Qiyuan Chen, Jiaying He, Jintai Chen, Hongxia Xu, Jian Wu

ECCV 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 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 GGR gradient rectificationIOMatch · CIFAR-10 6/4 split, 5 labels/class (closed-set)accuracy: 89.87 -> 91.87Improved
add GGR gradient rectificationDAC · CIFAR-10 6/4 split, 5 labels/class (closed-set)accuracy: 86.69 -> 87.63Improved
add GGR gradient rectificationOpenMatch · CIFAR-10 6/4 split, 5 labels/class (closed-set)accuracy: 47.26 -> 47.38No clear effect
add GGR gradient rectificationIOMatch · CIFAR-100 20/80 split, 5 labels/class (closed-set)accuracy: 56.48 -> 56.75No clear effect
add GGR gradient rectificationIOMatch · ImageNet-30 20/10, 1% labelsaccuracy: 85.18 -> 85.90Improved
add GGR gradient rectificationDAC · ImageNet-30 20/10, 1% labelsaccuracy: 86.40 -> 87.40Improved
add GGR gradient rectificationOpenMatch · ImageNet-30 20/10, 5% labels (open-set)balanced accuracy: 61.51 -> 68.15Improved
add GGR gradient rectificationDAC · CIFAR-100 50/50 split, 5 labels/class (open-set BA)balanced accuracy: 54.65 -> 53.77Hurt
apply GGR to head instead of backbone (ablation)DAC · CIFAR-10 6/4 split, 5 labels/class (closed-set)accuracy: 87.63 -> 90.38Improved
apply GGR to both backbone and head instead of backbone (ablation)IOMatch · CIFAR-10 6/4 split, 5 labels/class (closed-set)accuracy: 91.87 -> 89.56Hurt
apply GGR to both backbone and head instead of backbone (ablation)DAC · CIFAR-100 50/50 split, 5 labels/class (closed-set)accuracy: 57.19 -> 58.50Improved
use CSR subspace rectification instead of VLR (ablation)DAC · CIFAR-100 50/50 (efficiency study)accuracy: 56.90 -> 57.26Improved

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