AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Unified Perceptual Parsing for Scene Understanding

Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun

ECCV 2018 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 2,344 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 Pyramid Pooling Module to FPN (ablation)FPN (/4) with ResNet-50 · ADE20K val (object parsing)mean IoU / pixel accuracy: 4.87/3.09Improved
fuse features from all FPN levels (ablation)FPN+PPM (/4) · ADE20K val (object parsing)mean IoU: 40.13 -> 41.22Improved
increase FPN output resolution from /16 to /4 (ablation)FPN · ADE20K val (object parsing)mean IoU: 34.46 -> 35.26Improved
use FPN instead of dilated network (ablation)FPN (/16) vs DilatedNet reproduced · ADE20K val (object parsing)training time (hr): 18.1 vs 53.9 hr; mIoU 34.46 vs 34.28Improved
use UPerNet instead of PSPNet (ablation)UPerNet ResNet-50 · ADE20K val (object parsing)training time (hr): 61.1 -> 38.7Improved
add part annotations to object training (ablation)UPerNet · Broden+ val (object)mean IoU: 24.72 -> 23.92No clear effect
add scene classification branch (ablation)UPerNet object+part · Broden+ val (object)mean IoU: 23.92 -> 23.83No clear effect
add material parsing to joint training (ablation)UPerNet object+part+scene · Broden+ val (object)mean IoU: 23.83 -> 23.36Hurt
add material parsing to joint training (ablation)UPerNet object+part+scene · Broden+ val (part)mean IoU with background: 30.10 -> 28.75Hurt
train material jointly with object, part and scene (ablation)UPerNet · Broden+ val (material)mean IoU: 52.78 -> 54.19Improved
add part annotations to object trainingUPerNet · Broden+ val (part)mean IoU with background: 30.21Mixed
fine-tune texture branch separately after other tasks (not mixed in)UPerNet · Broden+ val (texture)top-1 accuracy: 35.10Mixed

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