AI Paper Atlas

Research map / Detection and segmentation / CNN features

PSANet: Point-wise Spatial Attention Network for Scene Parsing

Hengshuang Zhao, Yi Zhang, Shu Liu, Jianping Shi, Chen Change Loy, Dahua Lin, Jiaya Jia

ECCV 2018 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 1,245 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 COLLECT branch (ablation)ResNet-50 FCN baseline · ADE20K val (SS)mIoU (%): 37.23 -> 41.27Improved
add DISTRIBUTE branch to COLLECT (bi-direction) (ablation)PSANet ResNet-50 · ADE20K val (SS)mIoU (%): 41.27 -> 41.92Improved
add DISTRIBUTE branch to COLLECT (bi-direction) (ablation)PSANet ResNet-101 · ADE20K val (SS)mIoU (%): 42.70 -> 42.75Improved
use over-complete masks with relative location instead of compact masks (ablation)PSA COLLECT ResNet-50 · ADE20K val (SS)mIoU (%): 41.07 -> 41.27Improved
replace non-local correlation masks with learned compact PSA masks (ablation)ResNet-50 · ADE20K val (SS)mIoU (%): 40.93 -> 41.07Improved
add PSA module (COLLECT+DISTRIBUTE) instead of PSP poolingResNet-50 · ADE20K val (SS)mIoU (%): 41.68 -> 41.92Improved
add DenseCRF post-processingResNet-50 baseline · ADE20K val (SS)mIoU (%): 37.23 -> 37.97No clear effect
add PSA module (COLLECT+DISTRIBUTE) (ablation)ResNet-50 · VOC 2012 val (SS)mIoU (%): 67.12 -> 77.24Improved
add PSA module (COLLECT+DISTRIBUTE) (ablation)ResNet-101 · VOC 2012 val (SS)mIoU (%): 70.64 -> 78.51Improved
add DISTRIBUTE to COLLECT (ablation)ResNet-101 · VOC 2012 val (SS)mIoU (%): 77.90 -> 78.51Improved
add PSA module (COLLECT+DISTRIBUTE) (ablation)ResNet-50 · Cityscapes val (SS)mIoU (%): 71.93 -> 76.65Improved
add PSA module (COLLECT+DISTRIBUTE) (ablation)ResNet-101 · Cityscapes val (SS)mIoU (%): 74.83 -> 77.94Improved

Later papers that compared with this method

14 later accepted papers report PSANet50 as a baseline in their results tables; 14 of them report a better number on most of the results they share with it.

6 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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