AI Paper Atlas

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

Bridging Granularity Gaps: Hierarchical Semantic Learning for Cross-domain Few-shot Segmentation

Sujun Sun, Haowen Gu, Cheng Xie, Yanxu Ren, Mingwu Ren, Haofeng Zhang

AAAI 2026 · 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 Dual Style Randomization (ablation)HSL ResNet-50 baseline · CD-FSS avg 1-shotmIoU: 57.82 -> 60.44Improved
add Dual Style Randomization (ablation)HSL ViT-B/16 baseline · CD-FSS avg 1-shotmIoU: 62.24 -> 64.55Improved
add Hierarchical Semantic Mining (ablation)HSL ResNet-50 baseline · CD-FSS avg 1-shotmIoU: 57.82 -> 60.92Improved
add Hierarchical Semantic Mining (ablation)HSL ViT-B/16 baseline · CD-FSS avg 1-shotmIoU: 62.24 -> 65.29Improved
add PCMT on top of DSR+HSM (ablation)HSL ViT-B/16 · CD-FSS avg 1-shotmIoU: 67.05 -> 68.24Improved
add PCMT on top of DSR+HSM (ablation)HSL ResNet-50 · CD-FSS avg 1-shotmIoU: 62.97 -> 64.23Improved
use all four superpixel scales instead of only the finest (ablation)HSL ViT-B/16 · CD-FSS avg 1-shotmIoU: 65.43 -> 67.05Improved
use PCMT instead of OTSU threshold (ablation)HSL ViT-B/16 · CD-FSS avg 1-shotmIoU: 67.95 -> 68.24Improved
use OTSU threshold instead of fixed 0 (ablation)HSL ViT-B/16 · ISIC 1-shotmIoU: 55.79 -> 59.98Improved
use OTSU threshold instead of fixed 0 (ablation)HSL ViT-B/16 · FSS-1000 1-shotmIoU: 81.93 -> 80.43Hurt
use HSL instead of DRAResNet-50 · CD-FSS avg 1-shotmIoU: 60.86 -> 64.23Improved
use HSL instead of LoECViT-B/16 · CD-FSS avg 5-shotmIoU: 70.43 -> 72.32Improved

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