AI Paper Atlas

Research map / Detection and segmentation / CNN features

RDFNet: RGB-D Multi-Level Residual Feature Fusion for Indoor Semantic Segmentation

Seong-Jin Park, Ki-Sang Hong, Seungyong Lee

ICCV 2017 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 298 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 depth (HHA) via multi-modal fusion to RefineNet-152RefineNet Res-152 · NYUDv2mean IoU: 46.5 -> 50.1Improved
replace multi-level concatenation fusion with MMFNet fusion (ablation)RDF-101 · NYUDv2mean IoU: 47.0 -> 49.1Improved
add residual pooling (ablation)RDF-101 · NYUDv2mean IoU: 48.7 -> 49.1Improved
add adaptive-weight convolution in fusion (ablation)RDF-101 · NYUDv2mean IoU: 47.7 -> 49.1Improved
add skip connection in RCUs (ablation)RDF-101 · NYUDv2mean IoU: 45.8 -> 49.1Improved
deeper backbone ResNet-50 to ResNet-101RDFNet · NYUDv2mean IoU: 47.7 -> 49.1Improved
deeper backbone ResNet-101 to ResNet-152RDFNet · NYUDv2mean IoU: 49.1 -> 50.1Improved
use raw scaled depth instead of HHA encodingRDF-101 · NYUDv2mean IoU: 49.1 -> 48.2Hurt
use RefineNet instead of FCN32 for HHA-only inputdepth-only network · NYUDv2mean IoU: 25.2 -> 36.3Improved

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