AI Paper Atlas

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

Undoing the Damage of Label Shift for Cross-Domain Semantic Segmentation

Yahao Liu, Jinhong Deng, Jiale Tao, Tong Chu, Lixin Duan, Wen Li

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 22 citations (OpenAlex)

Check 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
Apply inference adjustment after conditional alignmentFADA · GTA5 to CityscapesmIoU: 46.9 -> 48.8Improved
Apply classifier refinement after conditional alignmentFADA · GTA5 to CityscapesmIoU: 46.9 -> 49.0Improved
Add classifier rectificationFADA · SYNTHIA to CityscapesmIoU: 40.9 -> 42.5; 40.9 -> 43.0Improved
Add classifier rectification to ProDAProDA · GTA5 to CityscapesmIoU: 57.5 -> 59.3; 1.8Improved
Add classifier rectification to ProDAProDA · SYNTHIA to CityscapesmIoU: 55.5 -> 56.7Improved
Add classifier rectification to ProDAProDA · SYNTHIA to CityscapesmIoU* (13 classes): 62.0 -> 64.5Improved
Add classifier rectification to IASTIAST · GTA5 to CityscapesmIoU: 51.5 -> 55.5; 53.0 -> 55.5; 2.5%Improved
Add classifier rectification to self-distillationFADA+SD · GTA5 to CityscapesmIoU: 49.2 -> 52.7; 3.5Improved
Use inference adjustment with Modified ASPP instead of Original ASPP (ablation)Our IA · GTA5 to CityscapesmIoU: 48.8 -> 49.2Improved
Use classifier refinement with Modified ASPP instead of Original ASPP (ablation)Our CR · GTA5 to CityscapesmIoU: 49.0 -> 48.7Hurt

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