AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Deep Floor Plan Recognition Using a Multi-Task Network With Room-Boundary-Guided Attention

Zhiliang Zeng, Xianzhi Li, Ying Kin Yu, Chi-Wing Fu

ICCV 2019 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 160 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 shared features and spatial contextual module (vs two separate single-task networks) (ablation)floor plan network · R3Doverall accuracy: 0.82 -> 0.89Improved
add shared features and spatial contextual module (vs two separate single-task networks) (ablation)floor plan network · R3Daverage class accuracy: 0.72 -> 0.80Improved
add spatial contextual module (ablation)floor plan network · R3Doverall accuracy: 0.85 -> 0.89Improved
add spatial contextual module (ablation)floor plan network · R3Daverage class accuracy: 0.72 -> 0.80Improved
add room-boundary-guided attention (ablation)spatial contextual module · R3Doverall accuracy: 0.86 -> 0.89Improved
add room-boundary-guided attention (ablation)spatial contextual module · R3Daverage class accuracy: 0.74 -> 0.80Improved
add direction-aware kernels (ablation)spatial contextual module · R3Doverall accuracy: 0.87 -> 0.89Improved
add direction-aware kernels (ablation)spatial contextual module · R3Daverage class accuracy: 0.77 -> 0.80Improved
add postprocessing (connected regions, majority room type)floor plan network · R2Voverall accuracy: 0.88 -> 0.89Improved
add postprocessing to baselines DeepLabV3+DeepLabV3+ · R3Doverall accuracy: 0.85 -> 0.83Hurt
use floor plan network vs DeepLabV3+floor plan network · R3Dmean IoU: 0.50 -> 0.63Improved
use floor plan network vs RCF edge detector for wallsfloor plan network · R3DF-measure max: 0.68 -> 0.95Improved

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