AI Paper Atlas

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

Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation

Junyuan Ma, Xunzhi Xiang, Wenbin Li, Qi Fan, Yang Gao

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 Hierarchical Layer Selection (HLS) (ablation)SSP baseline · CD-FSS avg 5-shot (DINOv3)mIoU: 63.1 -> 76.7Improved
add Prior Guided Regularization on top of HLS (ablation)SSP + HLS · CD-FSS avg 5-shot (DINOv3)mIoU: 76.7 -> 77.3Improved
add Pixelwise Adaptive Calibration on top of HLS (ablation)SSP + HLS · CD-FSS avg 5-shot (DINOv3)mIoU: 76.7 -> 77.2Improved
add both PGR and PAC on top of HLS (ablation)SSP + HLS · CD-FSS avg 5-shot (DINOv3)mIoU: 76.7 -> 77.9Improved
use ETR-based HLS instead of Static-Max heuristic selector (ablation)HERA layer routing · CD-FSS avg 5-shot (DINOv3)mIoU: 71.9 -> 76.7Improved
use ETR-based HLS instead of gradient-norm selector (ablation)HERA layer routing · CD-FSS avg 5-shot (DINOv3)mIoU: 73.1 -> 76.7Improved
use ETR-based HLS instead of Static-Max on DINOv2 (ablation)HERA layer routing · CD-FSS avg 5-shot (DINOv2)mIoU: 64.0 -> 72.6Improved
make MLP at routed layer trainable at test time rather than frozen (ablation)HERA · CD-FSS avg 5-shot (DINOv3)mIoU: 75.78 -> 77.91Improved
add all three PAC branches (sim, attn, img) versus a single branch (ablation)HLS+PGR · CD-FSS avg 5-shot (DINOv3)mIoU: 77.27 -> 77.91Improved
include L23 in local fusion candidates with tau=2.0 (ablation)HERA local fusion · CD-FSS avg 5-shot (DINOv3)mIoU: 75.49 -> 77.85Improved
keep PAC gate automatic (T=2) rather than off in 5-shot (ablation)HERA PAC · CD-FSS avg 5-shot (DINOv3)mIoU: 76.67 -> 77.91Improved
use PAC always on versus automatic gate in 1-shot (ablation)HERA PAC · CD-FSS avg 1-shot (DINOv3)mIoU: 68.02 -> 68.29Improved

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