AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Geometry-Aware Network for Domain Adaptive Semantic Segmentation

Yinghong Liao, Wending Zhou, Xu Yan, Zhen Li, Yizhou Yu, Shuguang Cui

AAAI 2023 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 6 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 GANDA geometry-aware adaptationHRDA · GTA5 → CityscapesmIoU: 73.8 -> 74.5Improved
Add GANDA geometry-aware adaptationHRDA · GTA5 → Cityscapess-mIoU: 68.2 -> 69.0Improved
Add GANDA geometry-aware adaptationHRDA · SYNTHIA → CityscapesmIoU: 65.8 -> 67.0Improved
Add GANDA geometry-aware adaptationProDA · SYNTHIA → CityscapesmIoU: 51.9 -> 54.5Improved
Add depth estimation to image-only adversarial adaptation (ablation)ProDA adaptation · SYNTHIA → CityscapesmIoU: 40.9 -> 41.2Improved
Add the semantic-geometric consistency loss (ablation)GAA self-training · SYNTHIA → CityscapesmIoU: 51.9 -> 52.3Improved
Add the geometric adaptation module (ablation)GAA self-training · SYNTHIA → CityscapesmIoU: 51.9 -> 52.9Improved
Use weighted cross-entropy loss (ablation)GAA self-training · SYNTHIA → CityscapesmIoU: 51.9 -> 53.1Improved
Combine self-training, GA, WCE, and SGC (ablation)GAA · SYNTHIA → CityscapesmIoU: 51.9 -> 54.5Improved

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