AI Paper Atlas

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

Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation

Siyu Chen, Ting Han, Changshe Zhang, Xin Luo, Meiliu Wu, Guorong Cai, Jinhe Su

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 9 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 depth-aware tokens, depth awareness, attention optimization and DRD (full DepthForge) to REIN (ablation)REIN (DINOv2-L) · Cityscapes->ACDC SnowmIoU: 70.6 -> 75.4Improved
concatenate depth features f_d to REIN (ablation)REIN (DINOv2-L) · Cityscapes->ACDC SnowmIoU: 70.6 -> 70.8No clear effect
use Prompt Depth Anything instead of Depth Anything V2 (ablation)DepthForge · Cityscapes->ACDC Snow (DINOv2-L)mIoU: 71.5 -> 70.4Hurt
add Depth Anything V2 features (ablation)REIN (DINOv2-L) · Cityscapes->ACDC SnowmIoU: 70.6 -> 71.5Improved
add Depth Refinement Decoder (ablation)REIN + Depth Anything V2 · Cityscapes->ACDC SnowmIoU: 71.5 -> 72.0Improved
add depth awareness and attention optimization (ablation)REIN + DRD · Cityscapes->ACDC SnowmIoU: 72.0 -> 72.2Improved
use depth-aware learnable tokens (full design) instead of depth token design (ablation)DepthForge · Cityscapes->ACDC (avg gain)average gain: 1.6 -> 3.5Improved
concatenate depth to input instead of no depth (ablation)REIN · Cityscapes->ACDC (avg gain)average gain: -1.1Hurt
add scale factor (ablation)DepthForge · Cityscapes->ACDC (avg gain)average gain: 2.8 -> 3.5Improved
apply DepthForge on EVA02-L backboneREIN (EVA02-L) · Cityscapes->ACDC SnowmIoU: 66.0 -> 69.5Improved
DepthForge vs FADA on GTA5->CityscapesFADA · GTA5->CityscapesmIoU: 68.23 -> 69.04Improved
DepthForge vs FADA on Mapillary (Cityscapes source)FADA · Cityscapes->MapillarymIoU: 75.86 -> 75.93No clear effect

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