AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning Compositional Neural Information Fusion for Human Parsing

Wenguan Wang, Zhijie Zhang, Siyuan Qi, Jianbing Shen, Yanwei Pang, Ling Shao

ICCV 2019 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 146 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
parse the whole human hierarchy with direct inference instead of only leaf parts (ablation)backbone direct inference · PASCAL-Person-Part testmIoU (1st level): 64.14 -> 65.27Improved
add bottom-up inference to direct inference (ablation)direct model · PASCAL-Person-Part testmIoU (1st level): 65.27 -> 65.42Improved
add top-down inference to direct inference (ablation)direct model · PASCAL-Person-Part testmIoU (1st level): 65.27 -> 69.02Improved
add bottom-up inference on top of direct + top-down (ablation)direct + top-down · PASCAL-Person-Part testmIoU (1st level): 69.02 -> 69.43Improved
add bottom-up inference on direct + top-down for 3rd level full body (ablation)direct + top-down · PASCAL-Person-Part test (3rd level)mIoU: 88.40 -> 91.02Improved
add confidence-conditioned fusion gates (ablation)direct + bottom-up + top-down · PASCAL-Person-Part testmIoU (1st level): 69.43 -> 70.76Improved
add confidence-conditioned fusion gates (ablation)direct + bottom-up + top-down · PASCAL-Person-Part test (2nd level)mIoU: 80.34 -> 81.62Improved
add confidence-conditioned fusion gates (ablation)direct + bottom-up + top-down · PASCAL-Person-Part test (3rd level)mIoU: 91.02 -> 91.31Improved
use full compositional fusion model instead of CE2Phuman parser · LIP valmIoU: 53.10 -> 57.74Improved
use full compositional fusion model instead of MuLAhuman parser · LIP valpixel accuracy: 88.5 -> 88.03Hurt
use full compositional fusion model instead of TGPNethuman parser · Fashion Clothing testF-1 score: 51.92 -> 58.12Improved

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