AI Paper Atlas

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

Semi-supervised Semantic Segmentation via Strong-weak Dual-branch Network

Wenfeng Luo, Meng Yang

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 89 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 9k weak annotations to 1.4k strong ones in a single-branch network (ablation)single-branch VGG16 · PASCAL VOC valmIoU: 68.9 -> 62.8Hurt
use a strong-weak dual-branch network instead of single branch with same data (ablation)VGG16 segmentation net · PASCAL VOC valmIoU: 62.8 -> 72.2Improved
add oversampling of strong data to dual-branch network (ablation)dual-branch VGG16 · PASCAL VOC valmIoU: 66.4 -> 72.2Improved
oversample strong annotations in single-branch network (ablation)single-branch VGG16 · PASCAL VOC valmIoU: 62.8 -> 65.9Mixed
use 10k strong annotations in the weak branch instead of 1.4k strong + 9k weak (ablation)dual-branch VGG16 · PASCAL VOC valmIoU: 72.2 -> 73.9Improved
ensemble separate strong and weak networks with lambda 0.4 (ablation)strong-only network · PASCAL VOC valmIoU: 68.9 -> 70.8Improved
add weak branch (dual-branch) on top of 1.4k strong only (ablation)strong-only single branch · PASCAL VOC valmIoU: 68.9 -> 72.2Improved
dual-branch with weak labels vs single-branch trained on 10k strongdual-branch VGG16 · PASCAL VOC valmIoU: 71.4 -> 72.2Improved
add 98k weak annotations to 20k strong in single-branch network (ablation)single-branch · COCO valmean IoU: 46.1 -> 33.4Hurt
use dual-branch network with 98k weak annotations (ablation)dual-branch · COCO valmean IoU: 33.4 -> 47.6Improved
switch backbone from VGG16 to ResNet101dual-branch · PASCAL VOC testmIoU: 72.3 -> 77.1Improved

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