AI Paper Atlas

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

Hierarchical Prompt Injector for Domain Generalization Segmentation

Xin Kun Lin, Ruoyu Guo, Jiaqi Guo, Maurice Pagnucco, Yang Song

ECCV 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 Region Cue to prompts (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.28 -> 70.62Improved
add Part description to prompts (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.40 -> 70.62Improved
add Geometry description to prompts (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.44 -> 70.62Improved
add Boundary Relation to prompts (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.74 -> 70.62Improved
use R=3 regional prompts instead of 2 (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.48 -> 70.62Improved
use R=3 regional prompts instead of 4 (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.69 -> 70.62Improved
add SAC gating (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.73 -> 70.62Improved
add SCC gating (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.94 -> 70.62Improved
add spatial localization loss (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.54 -> 70.62Improved
add semantic consistency loss (ablation)HPI (CLIP-L+DINOv2-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 69.91 -> 70.62Improved
add DINOv2 branch (ablation)HPI (CLIP-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 60.33 -> 70.62Improved
add DINOv2 branch (ablation)HPI (EVA02-L) · G->{C,B,M} (synthetic-to-real) averagemIoU: 66.63 -> 69.39Improved

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