AI Paper Atlas

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

Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier

Prantik Howlader, Srijan Das, Hieu Le, Dimitris Samaras

ECCV 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 26 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 MPMC plug-in to AugSeg, AEL, U2PL, UniMatchsemi-supervised segmentation baselines · PASCAL VOC Classic 1/16 (ResNet-101)mIoU: 75.2 -> 77.3 (UniMatch)Improved
add MPMC to baselines on CityscapesUniMatch · Cityscapes val 1/16 (ResNet-101)mIoU: 76.6 -> 78.5Improved
add MPMC to baselines on medical ACDCUniMatch · ACDC 3 casesDSC: 88.9 -> 91.8Improved
add MPMC to baselines on ACDC with more labelsUniMatch · ACDC 7 casesDSC: 89.9 -> 90.4Improved
add MPMC on labeled images only (ablation)basic teacher-student · Cityscapes 1/16mIoU: 68.4 -> 70.8Improved
add MPMC on unlabeled images (adaptive weights) on top of labeled-only MPMC (ablation)basic teacher-student · Cityscapes 1/16mIoU: 70.8 -> 73.1Improved
use three scales (original, 7x7, 19x19) instead of a single scale (ablation)MPMC · Cityscapes 1/16 (AugSeg)mIoU: 74.1 -> 75.3Improved
plug MPMC in encoder layer 1 instead of decoder end (ablation)MPMC · PASCAL VOCmIoU: 75.8 -> 77.3Improved
set beta of unsupervised multi-label loss to 0.15 instead of 0 (ablation)MPMC + UniMatch · Cityscapes 1/16mIoU: 77.5 -> 78.5Improved
increase alpha above 0.25 (0.45) (ablation)MPMC + UniMatch · Cityscapes 1/16mIoU: 78.5 -> 76.9Hurt
add MPMC to ViT-L based AugSegAugSeg (Seg-L) · Cityscapes 1/16mIoU: 56.6 -> 58.0Improved
add MPMC (patch-level) in patches with low multi-label accuracybasic teacher-student · Cityscapes patch analysisavg mIoU delta: +4.05 (90+) vs -2.20 (0-10)Mixed

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