atlas

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

Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation

AAAI 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 20 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 cross-domain grouping with group-level domain alignment instead of global alignment (K=1) (ablation)Cross-domain grouping and alignment · GTA5 → CityscapesmIoUHelped
Increase the number of groups through K=8 (ablation)Cross-domain grouping and alignment · GTA5 → Cityscapes and SYNTHIA → CityscapesmIoUHelped
Use more than the best grouping granularity, K=8 (ablation)Cross-domain grouping and alignment · GTA5 → Cityscapes and SYNTHIA → CityscapesmIoUHurt
Add semantic consistency loss L_co (ablation)Group-level adversarial alignment · GTA5 → CityscapesmIoU: 48.8 -> 49.1Helped
Add orthogonality loss L_orth (ablation)Group-level adversarial alignment with semantic consistency · GTA5 → CityscapesmIoU: 49.1 -> 50.8Helped
Add group-level class equivalence loss L_cl (ablation)Group-level alignment with semantic consistency and orthogonality · GTA5 → CityscapesmIoU: 50.8 -> 51.5Helped

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