AI Paper Atlas

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

SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domains

Qingmei Li, Yang Zhang, Peifeng Zhang, Haohuan Fu, Juepeng Zheng

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 0 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 prompt normalization (ablation)SAGE APF · Cityscapes -> {B,M,G,S} avgmIoU: 40.63 -> 41.85Improved
add softmax after prompt normalization (ablation)SAGE APF · Cityscapes -> {B,M,G,S} avgmIoU: 41.85 -> 42.17Improved
add tanh after normalization and softmax (ablation)SAGE APF · Cityscapes -> {B,M,G,S} avgmIoU: 42.17 -> 43.90Improved
add softmax alone without normalization (ablation)SAGE APF · Cityscapes -> {B,M,G,S} avgmIoU: 40.63 -> 40.49Hurt
add tanh alone (ablation)SAGE APF · Cityscapes -> {B,M,G,S} avgmIoU: 40.63 -> 41.59Improved
add modulation network to border prompt (A-Border vs Border) (ablation)SAGE prompt generator · GTAV -> {C,B,M,S} avgmIoU: 40.75 -> 42.09Improved
add modulation network to border prompt (A-Border vs Border) (ablation)SAGE prompt generator · SYNTHIA -> {C,B,M,G} avgmIoU: 36.84 -> 37.88Improved
add modulation to full-image prompt (A-Full vs Full) (ablation)SAGE prompt generator · GTAV -> {C,B,M,S} avgmIoU: 40.76 -> 40.80No clear effect
use border prompt instead of full-image prompt (adaptive) (ablation)SAGE prompt generator · GTAV -> {C,B,M,S} avgmIoU: 40.80 -> 42.09Improved
use meta initialization instead of zero init (ablation)SAGE prompt template · GTAV -> {C,B,M,S} avgmIoU: 40.76 -> 42.09Improved
use meta initialization instead of uniform init (ablation)SAGE prompt template · SYNTHIA -> {C,B,M,G} avgmIoU: 36.89 -> 37.88Improved
use four styles (L,P,V,Vo) instead of three (L,P,V) (ablation)SAGE style set · Cityscapes -> {B,M,G,S} avgmIoU: 38.26 -> 43.90Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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