AI Paper Atlas

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

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

Hanzhe Hu, Fangyun Wei, Han Hu, Qiwei Ye, Jinshi Cui, Liwei Wang

NeurIPS 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 14 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
Use AEL instead of Cutmix-SegDeepLabv3+ with ResNet-101 · Cityscapes val 1/32mIoU: 69.11 -> 74.28Improved
Use AEL instead of Cutmix-SegDeepLabv3+ with ResNet-101 · PASCAL VOC 2012 val 1/32mIoU: 73.39 -> 76.97Improved
Use AEL instead of Cutmix-SegDeepLabv3+ with ResNet-101 · ADE20K val 1/32mIoU: 26.15 -> 28.40Improved
Add dynamic re-weighting to the basic framework (ablation)AEL · Cityscapes val 1/32 and 1/16mIoU: +1.1% and +1.7%Improved
Add adaptive equalization sampling to the basic framework (ablation)AEL · Cityscapes val 1/32 and 1/16mIoU: +2.5% and +2.0%Improved
Add adaptive CutMix to the basic framework (ablation)AEL · Cityscapes val 1/32 and 1/16mIoU: +1.3% / +1.7%Improved
Add adaptive Copy-Paste to the basic framework (ablation)AEL · Cityscapes val 1/32 and 1/16mIoU: +0.5% / +0.5%Improved
Use confidence rather than entropy or margin as the AES indicator (ablation)AEL with AES · Cityscapes val 1/32 and 1/16mIoU: Ent: 71.38, 73.21; Conf: 72.51, 74.39; Margin: 70.86, 73.05Mixed
Set dynamic re-weighting gamma to 2 rather than 0 (ablation)AEL with dynamic re-weighting · Cityscapes val 1/32 and 1/16mIoU: 69.11 -> 70.27; 72.13 -> 73.85Improved
Set adaptive CutMix ratio threshold to 0.005 (ablation)AEL with adaptive CutMix · Cityscapes val 1/32 and 1/16mIoU: 73.43; 75.12Mixed
Set sampled category count K to 3 in adaptive Copy-Paste (ablation)AEL with adaptive Copy-Paste · Cityscapes val 1/32 and 1/16mIoU: K=1: 72.18, 74.85; K=3: 74.28, 75.83Improved
Set unsupervised loss weight alpha to 1.0 (ablation)AEL · Cityscapes val 1/32 and 1/16mIoU: alpha=0.5: 71.85, 74.61; alpha=1.0: 74.28, 75.83Improved

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