AI Paper Atlas

Research map / Detection and segmentation / CNN features

Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation

Zhenyu Zhang, Zhen Cui, Chunyan Xu, Zequn Jie, Xiang Li, Jian Yang

ECCV 2018 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 228 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 joint learning of segmentation with depth (ablation)TRL (ResNet-18) · NYU Depth v2 segmentationmean IoU: 42.0 -> 45.0Improved
add joint learning of segmentation with depth (ablation)TRL (ResNet-18) · SUN-RGBD segmentationmean IoU: 43.5 -> 46.3Improved
add joint learning of depth with segmentation (ablation)TRL (ResNet-18) · NYU Depth v2 depthrms: 0.547 -> 0.510Improved
add joint learning of depth with segmentation (ablation)TRL (ResNet-18) · SUN-RGBD depthrms: 0.517 -> 0.468Improved
add task-attentional modules (TAM) (ablation)TRL (ResNet-18) · NYU Depth v2 depthrms: 0.526 -> 0.510Improved
add task-attentional modules (TAM) (ablation)TRL (ResNet-18) · NYU Depth v2 segmentationmean IoU: 43.6 -> 45.0Improved
add historical experience propagation (ablation)TRL (ResNet-18) · NYU Depth v2 depthrms: 0.540 -> 0.510Improved
add historical experience propagation (ablation)TRL (ResNet-18) · NYU Depth v2 segmentationmean IoU: 42.2 -> 45.0Improved
add gate unit in TAM (ablation)TRL (ResNet-18) · NYU Depth v2 segmentationmean IoU: 44.7 -> 45.0Improved
add gate unit in TAM (ablation)TRL (ResNet-18) · NYU Depth v2 depthrms: 0.515 -> 0.510Improved
use full TRL instead of baseline with parallel decoders and cross-stitch (ablation)TRL (ResNet-18) · NYU Depth v2 depthrms: 0.545 -> 0.510Improved
predict at finer scale (scale-1 to final) (ablation)TRL (ResNet-18) · NYU Depth v2 segmentationmean IoU: 40.3 -> 45.0Improved

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