AI Paper Atlas

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

Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups

Peixia Li, Pulak Purkait, Thalaiyasingam Ajanthan, Majid Abdolshah, Ravi Garg, Hisham Husain, Chenchen Xu, Stephen Gould, Wanli Ouyang, Anton van den Hengel

ICCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 30 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 diverse learning groups and filter module to semi-supervised segmentation under 9% PL noise (ablation)PS-MT · Pascal VOC 2012, 1/8 labelled, 9% PLmIoU (%): 65.1 -> 74.0Improved
add filter module to the two-LG framework (ablation)Ours · Pascal VOC 2012, 1/8 labelled, 9% PLmIoU (%): 69.9 -> 74.0Improved
add filter module to single-LG PS-MT (ablation)PS-MT (R50) · Pascal VOC 2012, 1/8 labelled, 9% PLmIoU (%): 65.1 -> 67.6Improved
use teacher from the other learning group for noise detection instead of own group (ablation)Ours · Pascal VOC 2012, 1/8 labelled, 9% PLmIoU (%): 72.4 -> 74.0Improved
use different architectures (R50 and PVTv2-B2) in the two learning groups instead of sameOurs · Pascal VOC 2012mIoUImproved
use CE+KL score instead of CE or KL alone for noise detectionfilter module · noise detectionF1 of noise detectionImproved
use proposed filter module instead of GMM for noise detectionfilter module · noise detectiondetected noise proportionImproved
apply method to clean-labelled semi-supervised segmentation (0% noise)Ours versus PS-MT · Pascal VOC 2012, 1/2 labelledmIoU (%): 77.88 -> 79.54Improved
apply method versus PS-MT under SCP noise at 1/2 labelsOurs versus PS-MT · Pascal VOC 2012, 9% SCPmIoU (%): 53.69 -> 75.95Improved
apply framework to weakly supervised segmentation with PVTv2 baselinePS-MT (PVTv2-B2) · Pascal VOC 2012 weakly supervisedmIoU (%): 66.7 -> 71.7Improved

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