AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning

Dongmin Park, Yooju Shin, Jihwan Bang, Youngjun Lee, Hwanjun Song, Jae-Gil Lee

NeurIPS 2022 · Label-efficient and robust learning › Noisy labels · approach: Loss correction and noise robustness theory · 6 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
remove the skyline constraint from the meta-network (ablation)MQ-Net · CIFAR10, noise 10%last test accuracy: 93.10 -> 87.25Hurt
remove the skyline constraint from the meta-network (ablation)MQ-Net · CIFAR10, noise 60%last test accuracy: 89.51 -> 81.67Hurt
replace self-validation set with random labeled validation set (ablation)MQ-Net · CIFAR10, noise 10%last test accuracy: 93.10 -> 92.10Hurt
replace self-validation set with random labeled validation set (ablation)MQ-Net · CIFAR10, noise 60%last test accuracy: 89.51 -> 87.65Hurt
use ReAct instead of CSI as purity score (CONF informativeness) (ablation)MQ-Net · CIFAR10, noise 40%last test accuracy: 91.43 -> 89.54Hurt
use CONF instead of LL as informativeness score (CSI purity) (ablation)MQ-Net · CIFAR10, noise 40%last test accuracy: 91.48 -> 91.43No clear effect
use CONF instead of LL as informativeness score (CSI purity) (ablation)MQ-Net · CIFAR10, noise 10%last test accuracy: 93.10 -> 93.28No clear effect
replace meta-objective with linear combination P(x)+I(x) (ablation)MQ-Net · CIFAR10, noise 20%, round 10test accuracy: 92.10 -> 89.49Hurt
replace meta-objective with multiplication P(x)*I(x) (ablation)MQ-Net · CIFAR10, noise 20%, round 10test accuracy: 92.10 -> 91.20Hurt
replace meta-objective with linear combination P(x)+I(x) (ablation)MQ-Net · CIFAR10, noise 40%, round 10test accuracy: 91.48 -> 88.86Hurt
replace meta-objective with multiplication P(x)*I(x) (ablation)MQ-Net · CIFAR10, noise 40%, round 10test accuracy: 91.48 -> 89.11Hurt
raise OOD labeling cost c_OOD from 0.5 to 4CONF · CIFAR10, noise 40%last test accuracy: 91.05 -> 80.06Hurt

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