AI Paper Atlas

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

Semi-Supervised Segmentation based on Error-Correcting Supervision

Robert Mendel, Luis Antonio de Souza Jr, David Rauber, João Paulo Papa, Christoph Palm

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 125 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 Error-Correcting Supervision with 1/8 labelsDeepLabv3+ ResNet50 · Pascal VOC 2012 val (1/8 labeled)mIoU: 65.20 -> 70.22Improved
add Error-Correcting Supervision with 1/8 labelsDeepLabv3+ ResNet50 · Cityscapes val (1/8 labeled)mIoU: 63.12 -> 67.38Improved
add Error-Correcting Supervision with 1/4 labelsDeepLabv3+ ResNet50 · Pascal VOC 2012 val (1/4 labeled)mIoU: 69.78 -> 72.60Improved
add Error-Correcting Supervision with 1/4 labelsDeepLabv3+ ResNet50 · Cityscapes val (1/4 labeled)mIoU: 67.31 -> 70.70Improved
add Error-Correcting Supervision with 1/2 labelsDeepLabv3+ ResNet50 · Pascal VOC 2012 val (1/2 labeled)mIoU: 73.42 -> 74.63Improved
add Error-Correcting Supervision with 1/2 labelsDeepLabv3+ ResNet50 · Cityscapes val (1/2 labeled)mIoU: 71.22 -> 72.89Improved
use Negated Focal Loss instead of Cross-Entropy on pseudo-labels (ablation)ECS lambda_cor 0.1 · Pascal VOC 2012 val (1/4 labeled)mIoU: 68.39 -> 72.60Improved
use Negated Focal Loss instead of Cross-Entropy on pseudo-labels (ablation)ECS lambda_cor 0.1 · Cityscapes val (1/4 labeled)mIoU: 69.27 -> 70.70Improved
add auxiliary corrector regularization (lambda_cor 0.1) to pseudo-label training (ablation)ECS with NFL · Pascal VOC 2012 val (1/4 labeled)mIoU: 71.97 -> 72.60Improved
add auxiliary regularization alone, without semi-supervised learning (ablation)supervised DeepLabv3+ · Pascal VOC 2012 val (1/4 labeled)mIoU: 69.79 -> 69.93No clear effect
add auxiliary regularization alone, without semi-supervised learning (ablation)supervised DeepLabv3+ · Cityscapes val (1/4 labeled)mIoU: 67.31 -> 68.22Improved
use a DeepLabv3+ discriminator with the adversarial method of Hung et al.adversarial semi-supervised baseline · Pascal VOC 2012 val (1/4 labeled)mIoU: 69.79 -> 65.83Hurt

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