AI Paper Atlas

Research map / Detection and segmentation / CNN features

UCTNet: Uncertainty-Aware Cross-Modal Transformer Network for Indoor RGB-D Semantic Segmentation

Xiaowen Ying, Mooi Choo Chuah

ECCV 2022 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 44 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 map as 4th input channelSwin-S RGB baseline · NYUv2mIoU (%): 52.2 -> 52.4Improved
add a separate depth encoder with element-wise add fusion (ablation)RGB-only Swin-S baseline · NYUv2mIoU (%): 52.2 -> 54.3Improved
use our fusion module instead of element-wise add (ablation)dual transformer encoders · NYUv2mIoU (%): 54.3 -> 55.3Improved
use our fusion module instead of SE-Add (ablation)dual transformer encoders · NYUv2mIoU (%): 54.6 -> 55.3Improved
use our fusion module instead of SA-Gate (ablation)dual transformer encoders · NYUv2mIoU (%): 53.8 -> 55.3Improved
replace standard depth encoder with UASA cut-off (ablation)UCTNet with our fusion · NYUv2mIoU (%): 55.3 -> 56.8Improved
replace standard depth encoder with UASA suppression (ablation)UCTNet with our fusion · NYUv2mIoU (%): 55.3 -> 57.6Improved
use UASA suppression instead of cut-off (ablation)UCTNet depth encoder · NYUv2mIoU (%): 56.8 -> 57.6Improved
raise temperature T from 5 to 15 (ablation)UASA suppression · NYUv2mIoU (%): 57.2 -> 57.6Improved
raise temperature T from 15 to 20 (ablation)UASA suppression · NYUv2mIoU (%): 57.6 -> 56.8Hurt
raise temperature T from 5 to 10 (ablation)UASA suppression · NYUv2mIoU (%): 57.2 -> 57.2No clear effect
UCTNet versus previous best without multi-scale testingUCTNet · NYUv2mIoU (%): 57.6Improved

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