AI Paper Atlas

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

PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation

Haoyu Xie, Changqi Wang, Jian Cun Zhao, Yang Liu, Jun Dan, Chong Fu, Baigui Sun

IJCV 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 36 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 probabilistic representation (ablation)contrastive teacher-student baseline · VOC 2012 classic (92 labels)mIoU: 66.91 -> 68.49Improved
add probabilistic representation (ablation)contrastive teacher-student baseline · VOC 2012 classic (732 labels)mIoU: 74.99 -> 76.00Improved
add global distribution prototype to PR (ablation)PR model · VOC 2012 classic (92 labels)mIoU: 68.49 -> 69.52Improved
add virtual negatives to PR (ablation)PR model · VOC 2012 classic (92 labels)mIoU: 68.49 -> 69.07Improved
add both GDP and virtual negatives to PR (ablation)PR model · VOC 2012 classic (92 labels)mIoU: 68.49 -> 70.23Improved
use GDP update instead of EMA prototype update (ablation)Baseline+ (EMA) vs PR+GDP · VOC 2012 classic (92 labels)mIoU: 68.27 -> 69.52Improved
add EMA prototype update to vanilla representation (ablation)Baseline · VOC 2012 classic (92 labels)mIoU: 66.91 -> 68.27Improved
add virtual negatives instead of memory bank (ablation)contrastive baseline with PR and GDP · VOC 2012 classic (92 labels)mIoU: 66.89 -> 68.01Improved
add memory bank of size 65536 (ablation)contrastive baseline with PR and GDP · VOC 2012 classic (92 labels)mIoU: 66.89 -> 67.11No clear effect
add memory bank of size 30000 (ablation)contrastive baseline with PR and GDP · VOC 2012 classic (92 labels)mIoU: 66.89 -> 66.05Hurt
add probabilistic representation and PRCL components to baselineBaseline · Cityscapes valSilhouette score: 0.2708 -> 0.3014Improved
use PRCL instead of baselineBaseline · VOC 2012 representation spaceSilhouette score: 0.3188 -> 0.3836Improved

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