AI Paper Atlas

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

Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation

Runmin Cong, Anpeng Wang, Bin Wan, Cong Zhang, Xiaofei Zhou, Wei Zhang

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 5 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 MGDF module to SSP+IFA baseline (ablation)DCDNet baseline · FSS-1000 (mIoU)mIoU: 80.1 -> 80.6Improved
add ACFD module before MGDF (ablation)DCDNet (MGDF) · FSS-1000 (mIoU)mIoU: 80.6 -> 81.3Improved
add CAM module during fine-tuning (ablation)DCDNet (MGDF+ACFD) · FSS-1000 (mIoU)mIoU: 81.3 -> 81.7Improved
decouple features into private and shared instead of base only (ablation)DCDNet fusion · FSS-1000 (mIoU)mIoU: 80.6 -> 81.4Improved
keep base feature in fusion with private and shared (ablation)DCDNet fusion · FSS-1000 (mIoU)mIoU: 81.4 -> 81.7Improved
add adversarial loss alone (ablation)DCDNet losses · FSS-1000 (mIoU)mIoU: 80.6 -> 81.0Improved
add contrastive loss alone (ablation)DCDNet losses · FSS-1000 (mIoU)mIoU: 80.6 -> 81.1Improved
combine adversarial and contrastive losses (ablation)DCDNet losses · FSS-1000 (mIoU)mIoU: 80.6 -> 81.5Improved
add orthogonality loss on top of adv+cont (ablation)DCDNet losses · FSS-1000 (mIoU)mIoU: 81.5 -> 81.7Improved
use DCDNet instead of IFA on ISIC 1-shotCD-FSS ResNet-50 · ISIC 1-shotmIoU: 66.3 -> 72.0Improved
use DCDNet instead of ABCDFSS on Chest X-Ray 5-shotCD-FSS ResNet-50 · Chest X-Ray 5-shotmIoU: 81.4 -> 81.1Hurt

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