AI Paper Atlas

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

TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks

YU LI, Min Li, Qiuxia LAI, Yannan Liu, Qiang Xu

NeurIPS 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Self-training theory · 13 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 contextual attributes (GNN on similarity graph) to intrinsic attributesTestRank · CIFAR-10 model AATPF: 67.47 -> 76.56 (vs DeepGini)Improved
combine intrinsic and contextual attributes instead of contextual only (ablation)TestRank · CIFAR-10 model AATPF: 51.39 -> 76.56Improved
use contextual attributes only vs random (ablation)TestRank Contextual-Only · CIFAR-10 model AATPF: 30.15 -> 51.39Improved
contextual-only vs DeepGini on model CTestRank Contextual-Only · SVHN model CATPF: 81.68 -> 93.99Improved
replace BYOL feature extractor with target model front layers (ablation)TestRank · CIFAR-10 / STL10ATPF: -6.23 average (76.56 -> 68.84 on CIFAR-10 A)Hurt
use approximate kNN graph instead of exact graph (ablation)TestRank · CIFAR-10/SVHN/STL10ATPF: +0.95 average influenceNo clear effect
vary number of neighbors k (20-800) (ablation)TestRank · STL10ATPFMixed

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