AI Paper Atlas

Research map / Detection and segmentation / CNN features

Cascaded Feature Network for Semantic Segmentation of RGB-D Images

Di Lin, Guangyong Chen, Daniel Cohen-Or, Pheng-Ann Heng, Hui Huang

ICCV 2017 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 155 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
use 3 depth-based branches instead of a single branch (ablation)CFN (VGG-16) · NYUDv2 validationmean IoU (%): 31.2 -> 35.5Improved
use 4 or 5 branches instead of 3 (larger super-pixels) (ablation)CFN (VGG-16) · NYUDv2 validationmean IoU (%): 35.5 -> 35.0 -> 34.6Hurt
add CaRF to single-branch network (ablation)VGG-FCN · NYUDv2 testmean IoU (%): 31.8 -> 32.0Improved
add CaRF to 3-branch network (ablation)CFN (VGG-16) · NYUDv2 testmean IoU (%): 31.7 -> 36.3Improved
add multiple branches without CaRF (ablation)VGG-FCN · NYUDv2 testmean IoU (%): 31.8 -> 31.7No clear effect
use CaRF instead of regular receptive fields (pooling kernels 3,5,7) (ablation)3-branch CFN · NYUDv2 testmean IoU (%): 33.8 -> 36.3Improved
add regular receptive fields to 3-branch network (ablation)3-branch CFN · NYUDv2 testmean IoU (%): 31.7 -> 33.8Improved
add cascaded links between branches (ablation)separate-branch CFN · NYUDv2 testmean IoU (%): 33.0 -> 36.3Improved
use separate contextual information per scene-resolution instead of shared (ablation)combined-branch CFN · NYUDv2 testmean IoU (%): 34.0 -> 36.3Improved
use deeper RefineNet-152 instead of VGG-16 in CFNCFN · NYUDv2 testmean IoU (%): 41.7 -> 47.7Improved
use deeper RefineNet-152 instead of VGG-16 in CFNCFN · SUN-RGBD testmean IoU (%): 42.5 -> 48.1Improved
add CFN to RefineNet-152 baseline (RGB-D)RefineNet-152 · NYUDv2 testmean IoU (%): 47.0 -> 47.7Improved

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