AI Paper Atlas

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

Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching

Sujun Sun, Mingwu Ren, Haofeng Zhang

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 1 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 SAFR feature re-fusion (ablation)baseline DINOv3 matching · Average 1-shotmIoU: 58.74 -> 62.53Improved
add SAFR feature re-fusion (ablation)baseline DINOv3 matching · Average 5-shotmIoU: 64.54 -> 68.64Improved
add ASE on top of SAFR (ablation)SAFR · Average 1-shotmIoU: 62.53 -> 66.16Improved
add HPM on top of SAFR (ablation)SAFR · Average 1-shotmIoU: 62.53 -> 65.99Improved
add HPM on top of SAFR+ASE (ablation)SAFR+ASE · Average 1-shotmIoU: 66.16 -> 68.39Improved
add HPM on top of SAFR+ASE (ablation)SAFR+ASE · Average 5-shotmIoU: 70.86 -> 73.08Improved
reduce residual weight of position-aware features instead of SAFR (ablation)baseline DINOv3 · Average 1-shotmIoU: 58.74 -> 58.28Hurt
variance regularization on position-sensitive channels (ablation)baseline DINOv3 · Average 1-shotmIoU: 58.74 -> 57.69Hurt
remove position-sensitive channels from F_last (ablation)baseline DINOv3 · Average 1-shotmIoU: 58.74 -> 62.15Improved
use SAFR instead of removing channels (ablation)position-sensitive channel removal · Average 1-shotmIoU: 62.15 -> 62.53Improved
add attention mask with fixed threshold 0.5 in ASE (ablation)ASE w/o mask · Average 1-shotmIoU: 63.76 -> 64.53Improved
use robust threshold instead of fixed threshold in ASE (ablation)ASE · Average 1-shotmIoU: 64.53 -> 66.16Improved

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