AI Paper Atlas

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

Exploration and Exploitation of Unlabeled Data for Open-Set Semi-supervised Learning

Ganlong Zhao, Guanbin Li, Yipeng Qin, Jinjin Zhang, Zhenhua Chai, Xiaolin K. Wei, Liang Lin, Yizhou Yu

IJCV 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 8 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 prototype clustering and identification (ablation)FixMatch · DomainNet-Real ID10/OOD50kaccuracy: 52.8 -> 55.0Improved
add prototype clustering and identification (ablation)FixMatch · DomainNet-Real ID20/OOD50kaccuracy: 49.7 -> 52.5Improved
cluster strong augmentations as well as weak ones (ablation)clustering · DomainNet-Real ID10/OOD50kaccuracy: 54.2 -> 55.0Improved
add cascading-pool importance sampling on top of clustering (ablation)Ours · DomainNet-Real ID10/OOD50kaccuracy: 55.0 -> 59.4Improved
add cascading-pool importance sampling on top of clustering (ablation)Ours · DomainNet-Real ID20/OOD50kaccuracy: 52.5 -> 54.3Improved
use importance-based selection instead of random selection of ID samples (ablation)Ours · DomainNet-Real ID10/OOD50kaccuracy: 57.2 -> 58.1Improved
add cascading pools to importance sampling (ablation)Ours · DomainNet-Real ID20/OOD50kaccuracy: 53.7 -> 54.3Improved
use two cascaded pools instead of zero pools (ablation)Ours · DomainNet-Real ID20/OOD50kaccuracy: 52.5 -> 54.3Improved
exploit OOD samples with SimCLR loss instead of masking them (ablation)FixMatch · DomainNet-Real ID20/OOD50kaccuracy: 54.3 -> 56.7Improved
mask OOD samples in FixMatch lossFixMatch · DomainNet-Real ID20/OOD50kaccuracy: 49.7 -> 54.3Improved
train with unlabeled OOD samples only (clustering) instead of labeled onlyOurs (Clustering) · CIFAR-100 ID10/OOD90 (extreme case)accuracy: 47.3 -> 73.5Improved
integrate the method into UDAUDA · CIFAR-100 ID10/OOD90accuracy: 38.9 -> 48.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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