AI Paper Atlas

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

Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning

Qing Yu, Daiki Ikami, Go Irie, Kiyoharu Aizawa

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 110 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 joint OOD-score optimization with curriculum selectionMixMatch · CIFAR-10, 250 labels, LSUN as OODaccuracy (%): 76.32 -> 86.65Improved
add joint OOD-score optimization with curriculum selectionMixMatch · CIFAR-10, 250 labels, Uniform as OODaccuracy (%): 72.90 -> 85.54Improved
add joint OOD-score optimization with curriculum selectionMixMatch · CIFAR-10, 250 labels, TIN as OODaccuracy (%): 82.42 -> 86.44Improved
add joint OOD-score optimization with curriculum selectionMixMatch · CIFAR-10, 4000 labels, TIN as OODaccuracy (%): 91.25 -> 93.03Improved
add joint OOD-score optimization with curriculum selectionMixMatch · SVHN, 250 labels, TIN as OODaccuracy (%): 94.66 -> 95.21Improved
add method when only 2000 OOD samples are in unlabeled dataMixMatch · CIFAR-10, 250 labels, LSUN OOD, 2000 OOD samplesaccuracy (%): 88.16 -> 84.82Hurt
increase number of OOD samples from 2000 to 20000 (baseline degrades, ours stable) (ablation)MixMatch · CIFAR-10, 250 labels, LSUN OODaccuracy (%): 88.16 -> 70.3 (baseline); 84.82 -> 85.83 (ours)Mixed
replace softmax or ODIN detection with joint-optimized OOD score (ablation)Hendrycks & Gimpel / ODIN · CIFAR-10 ID, TIN OOD (250 labels)OOD detection AUROC (%): 54.54 -> 98.86Improved
replace softmax or ODIN detection with joint-optimized OOD score (ablation)Hendrycks & Gimpel / ODIN · SVHN ID, Uniform OOD (250 labels)OOD detection AUROC (%): 2.79 -> 99.97Improved
replace UASD confidence filtering with explicit OOD detector trained on unlabeled data (ablation)UASD · CIFAR-10, 250 labels, LSUN as OODaccuracy (%): 80.87 -> 86.65Improved
replace UASD confidence filtering with explicit OOD detector trained on unlabeled data (ablation)UASD · CIFAR-10, 250 labels, TIN as OODdetection recall (%): 66.47 -> 99.22Improved
use natural-image outliers (TIN/LSUN) instead of synthetic noise outliers (ablation)MixMatch · CIFAR-10, 250 labels, baseline accuracyaccuracy (%): 72.90 -> 82.42Improved

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