AI Paper Atlas

Research map / Detection and segmentation / CNN features

FloorPlanFormer: Multi-Task Transformer Network for Floor Plan Recognition with Outer-to-Inner Feature Refinement

Yun Liang, ZiHao Wu, Run Zheng, Shuai Xie, Bo Hong, Yishen Lin

AAAI 2026 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 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 GCAM (ablation)FloorPlanFormer · FloorPlan8KmIoU: 0.919 -> 0.931Improved
add MFRM with small kernels (ablation)FloorPlanFormer · FloorPlan8KmIoU: 0.919 -> 0.932Improved
use small-kernel MFRM instead of large-kernel MFRM (ablation)FloorPlanFormer · FloorPlan8KTotal Accu.: 0.960 -> 0.964Improved
add GCAM and MFRM(S) together (ablation)FloorPlanFormer · FloorPlan8KmIoU: 0.919 -> 0.935Improved
add dice loss (ablation)FloorPlanFormer · FloorPlan8KTotal Accu.: 0.951 -> 0.964Improved
add cross-entropy loss (ablation)FloorPlanFormer · FloorPlan8KmIoU: 0.917 -> 0.922Improved
add joint multi-task loss (ablation)FloorPlanFormer · FloorPlan8KmIoU: 0.922 -> 0.935Improved
set MFRM repeat k=2 and N=3 vs k=1 (ablation)FloorPlanFormer · FloorPlan8KmIoU: 0.930 -> 0.935Improved
increase MFRM repeats to k=3 (ablation)FloorPlanFormer · FloorPlan8KmIoU: 0.935 -> 0.934No clear effect
base multi-task network vs Mask2formerFloorPlanFormer · FloorPlan8KTotal Accu.: mIoU 0.915 -> 0.919; Total Accu. 0.957 -> 0.951Mixed
FloorPlanFormer full vs DeepFloorplanFloorPlanFormer · FloorPlan8KmIoU: 0.793 -> 0.935Improved

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