AI Paper Atlas

Research map / Detection and segmentation / CNN features

Disentangled Non-local Neural Networks

Minghao Yin, Zhuliang Yao, Yue Cao, Xiu Li, Zheng Zhang, Stephen Lin, Han Hu

ECCV 2020 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 378 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 standard non-local blockdilated FCN R101 · Cityscapes valmIoU: 75.8 -> 78.5Improved
replace NL block by DNL block (both modifications) (ablation)NL · Cityscapes valmIoU: 78.5 -> 80.5Improved
change multiplication of terms to addition only (ablation)NL · Cityscapes valmIoU: 78.5 -> 79.2Improved
use non-shared key transform for unary term only (ablation)NL · Cityscapes valmIoU: 78.5 -> 79.0Improved
use pairwise term alone (ablation)dilated FCN R101 · Cityscapes valmIoU: 75.8 -> 77.5Improved
use unary term alone instead of both terms in NL (ablation)NL · Cityscapes valmIoU: 78.5 -> 79.3Improved
replace NL with DNLResNet-101 · Cityscapes testmIoU: 80.8 -> 82.0Improved
replace NL with DNLHRNetV2-W48 · Cityscapes testmIoU: 82.5 -> 83.0Improved
replace NL with DNLResNet-101 · ADE20K valmIoU: 44.67 -> 45.97Improved
replace NL with DNLResNet-101 · PASCAL-Context testmIoU: 50.6 -> 54.8Improved
replace NL with DNLMask R-CNN R50-FPN · COCO 2017 valAP bbox: 39.6 -> 40.3Improved
replace NL with DNLSlow-only R50 · Kinetics valtop-1 accuracy: 75.95 -> 76.31Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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