AI Paper Atlas

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

Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation

Prantik Howlader, Hieu Le, Dimitris Samaras

ECCV 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 5 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 per-pixel rank-statistics pseudo-label weighting plus detector-based reliable pixels to existing SSL frameworksUniMatch, AugSeg, AEL, U2PL · Pascal VOC Classic 1/16mIoU: AEL 66.1 -> 69.8 (ResNet-101)Improved
Add the method to the same four frameworks on CityscapesUniMatch, AugSeg, AEL, U2PL · Cityscapes val 1/16mIoU: AEL 74.5 -> 77.9 (ResNet-101)Improved
Add pseudo-label pixel weighting (prototypes from labeled pixels only) (ablation)basic teacher-student baseline · Pascal VOC Classic 1/16mIoU: +3.9%Improved
Add object-detector-based reliable pixel identification on top of weighting (ablation)basic teacher-student baseline · Pascal VOC Classic 1/16mIoU: +3.9% -> +7.4%Improved
Use rank statistics instead of cosine similarity for weightsUniMatch + Ours · Pascal VOC pseudo-label accuracypseudo-label accuracyImproved
Agreement between detector and segmentation model to select pixels (ablation)DeepLabv3+ R101 pseudo-labels · Pascal VOC 1/16pseudo-label accuracy: Cat 32.8 -> 41.7Improved
Vary k in top-k rank statisticsOurs · Pascal VOC 1/16, 1/8mIoUMixed
Raise detector confidence threshold from 0.85 to 0.95 (ablation)Ours (UniMatch) · Pascal VOC Classic 1/16mIoU: 76.7 -> 75.7Hurt
Increase memory bank size from 32 to 256 per class (ablation)Ours (UniMatch) · Pascal VOC Classic 1/16mIoU: 74.6 -> 76.7Improved
Set unsupervised loss weight alpha to 0.4 (ablation)Ours (UniMatch) · Pascal VOC Classic 1/16mIoU: 45.1 -> 76.7 (alpha 0 vs 0.4)Improved
Apply the weighting to a ViT-based method (SemiVL)SemiVL · Cityscapes 1/16mIoU: 77.9 -> 79.1Improved
Apply the weighting to UniMatch on MS COCOUniMatch (Xception-65) · MS COCO 1/512mIoU: 31.9 -> 33.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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