AI Paper Atlas

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

Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation

Lukas Hoyer, Dengxin Dai, Luc Van Gool

TPAMI 2023 · 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
add learning rate warmup (ablation)DeepLabV2 DG · GTA->Cityscapes DGmIoU: 25.2 -> 34.3Improved
add learning rate warmup (ablation)DeepLabV2 UDA · GTA->Cityscapes UDAmIoU: 49.1 -> 54.2Improved
replace ResNet with Transformer MiT encoder (ablation)SegFormer-style UDA · GTA->Cityscapes UDAmIoU: 54.2 -> 58.2Improved
add ImageNet thing-class feature distance (FD) (ablation)MiT UDA · GTA->Cityscapes UDAmIoU: 58.2 -> 61.7Improved
add rare class sampling (RCS) (ablation)MiT UDA · GTA->Cityscapes UDAmIoU: 58.2 -> 64.0Improved
use RCS instead of class-balanced sampling (T=infinity) (ablation)MiT UDA · GTA->Cityscapes UDAmIoU: 62.0 -> 64.0Improved
apply FD only to thing-classes (ablation)MiT UDA · GTA->CityscapesmIoU: +1.4/+2.9 mIoUImproved
stabilize self-training (ignore border pixels, alpha 0.999) (ablation)DAFormer UDA · GTA->Cityscapes UDAmIoU: 66.2 -> 67.0Improved
replace SegFormer decoder with DAFormer context-aware fusion decoder (ablation)MiT UDA · GTA->Cityscapes UDAmIoU: 67.0 -> 68.3Improved
restrict context fusion to bottleneck features only (ablation)DAFormer decoder · GTA->Cityscapes UDAmIoU: 68.3 -> 67.0Hurt
add multi-resolution training (HRDA) (ablation)DAFormer · GTA->Cityscapes UDAmIoU: 68.3 -> 73.8Improved
use learned scale attention instead of averaging scales (ablation)HRDA · GTA->Cityscapes UDAmIoU: 67.5 -> 71.5Improved

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