AI Paper Atlas

Research map / Detection and segmentation / CNN features

ShapeConv: Shape-Aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

Jinming Cao, Hanchao Leng, Dani Lischinski, Daniel Cohen-Or, Changhe Tu, Yangyan Li

ICCV 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 220 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 W_B only (no W_S) to the vanilla convolution (ablation)Deeplabv3+ ResNet-101 · NYUDv2-40Mean IoU: 45.9 -> 47.0Improved
add W_S only (no W_B) to the vanilla convolution (ablation)Deeplabv3+ ResNet-101 · NYUDv2-40Mean IoU: 45.9 -> 46.3Improved
add both W_B and W_S (full ShapeConv) (ablation)Deeplabv3+ ResNet-101 · NYUDv2-40Mean IoU: 45.9 -> 47.4Improved
use HHA instead of raw depth as input (ablation)Deeplabv3+ ResNet-101 · NYUDv2-40Mean IoU: 44.9 -> 45.9Improved
add depth input to RGB (ablation)Deeplabv3+ ResNet-101 · NYUDv2-40Mean IoU: 43.9 -> 44.9Improved
add multi-scale testing (ablation)Deeplabv3+ ResNet-101 (HHA) · NYUDv2-40Mean IoU: 45.9 -> 47.6Improved
replace vanilla conv by ShapeConv with Depth input (ablation)Deeplabv3+ ResNet-101 · NYUDv2-40Mean IoU: 44.9 -> 46.2Improved
replace vanilla conv by ShapeConv with HHA inputDeeplabv3+ ResNet-101 · NYUDv2-40Mean IoU: 45.9 -> 47.4Improved
replace vanilla conv by ShapeConvDeeplabv3+ ResNet-50 · NYUDv2-13Mean IoU: 60.8 -> 61.8Improved
replace vanilla conv by ShapeConvDeeplabv3+ ResNet-50 · SUN-RGBDMean IoU: 45.5 -> 46.3Improved
replace vanilla conv by ShapeConvDeeplabv3+ ResNet-101 · SIDMean IoU: 54.6 -> 60.6Improved
replace vanilla conv by ShapeConvUNet ResNet-50 · NYUDv2-40Mean IoU: 39.7 -> 42.0Improved

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