AI Paper Atlas

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

Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation

Seogkyu Jeon, Kibeom Hong, Hyeran Byun

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 3 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 texture perturbation (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 54.97 -> 55.38Improved
add consistency loss L_cons (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 55.38 -> 56.15Improved
add domain-aware contrastive prompt loss L_contra (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 56.15 -> 58.14Improved
add texture perturbation (Cityscapes target only) (ablation)DPMFormer (CLIP ViT-B) · GTAV to CityscapesmIoU: 57.5 -> 57.04Hurt
replace L_contra with CoCoOp contrastive loss (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 56.13 -> 56.36No clear effect
CoCoOp+ with augmented sample as positive (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 56.13 -> 56.20No clear effect
replace L_contra with PromptSRC (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 56.13 -> 56.78Improved
use similarity on prompt embeddings sim(pi,pi) instead of sim(t,t) (ablation)L_contra · GTAV to unseen (ViT-B), averagemIoU: 56.57 -> 58.14Improved
use sim(pi,pi) instead of sim(t,v) (ablation)L_contra · GTAV to unseen (ViT-B), averagemIoU: 57.34 -> 58.14Improved
lambda_cons 10 versus 1 (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 55.80 -> 58.14Improved
lambda_cons 10 versus 50 (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 56.98 -> 58.14Improved
temperature tau 0.5 versus 2 (ablation)DPMFormer (CLIP ViT-B) · GTAV to unseen (ViT-B), averagemIoU: 55.72 -> 58.14Improved

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