AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Xin Lai, Zhuotao Tian, Xiaogang Xu, Yingcong Chen, Shu Liu, Hengshuang Zhao, Liwei Wang, Jiaya Jia

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 58 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 decoupled network architecture with shallow-feature alignment instead of AdaptSegNet (ablation)AdaptSegNet · GTA5->CityscapesmIoU: +3.0% mIoUImproved
add Self-Discrimination (SD) (ablation)DecoupleNet · GTA5->CityscapesmIoU: 47.1 -> 49.0Improved
add Self-Discrimination (SD) (ablation)AdaptSegNet · GTA5->CityscapesmIoU: 44.1 -> 46.0Improved
add shallow-feature adversarial loss L_adv_low (ablation)DecoupleNet + SD · GTA5->CityscapesmIoU: +2.2% mIoUImproved
add output-space adversarial loss L_adv (ablation)DecoupleNet + SD · GTA5->CityscapesmIoU: 48.7 -> 49.0Improved
add auxiliary classifier for SD (ablation)DecoupleNet + SD · GTA5->CityscapesmIoU: 46.0 -> 49.0Improved
add class-wise thresholds for pseudo labels (ablation)DecoupleNet + SD · GTA5->CityscapesmIoU: 48.4 -> 49.0Improved
align source to target (phi_s -> phi_t) rather than target to source (ablation)DecoupleNet + SD · GTA5->CityscapesmIoU: 47.3 -> 49.0Improved
add shallow-feature alignment versus none (ablation)DecoupleNet + SD · GTA5->CityscapesmIoU: 46.8 -> 49.0Improved
decouple layer0 and layer1 instead of layer0 only or layer0-2 (ablation)DecoupleNet · GTA5->CityscapesmIoU: 47.7 / 49.0 / 47.9Mixed
use averaged full-image predictions versus fixed pseudo soft labels in OEST (ablation)OEST · GTA5->CityscapesmIoU: 55.6 -> 56.7Improved
average with full-image predictions instead of crop predictions in OEST (ablation)OEST · GTA5->CityscapesmIoU: 55.2 -> 56.7Improved

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