AI Paper Atlas

Research map / Detection and segmentation / CNN features

Asymmetric Non-Local Neural Networks for Semantic Segmentation

Zhen Zhu, Mengde Xu, Song Bai, Tengteng Huang, Xiang Bai

ICCV 2019 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 761 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 non-local block before classifier (ablation)FCN-like ResNet-101 baseline · Cityscapes valmIoU: 75.8 -> 78.4Improved
replace non-local block with APNB (ablation)ResNet-101 + NB · Cityscapes valmIoU: 78.4 -> 78.6No clear effect
replace non-local block with APNB for efficiencynon-local block · Cityscapes 256x128 inputGFLOPs: 601.4 -> 43.5Improved
replace non-local block with APNB for efficiencynon-local block · Cityscapes 256x128 inputGPU memory (MB): 7797 -> 277Improved
add common fusion of Stage4 and Stage5 (ablation)ResNet-101 baseline · Cityscapes valmIoU: 75.8 -> 76.5Improved
replace common fusion with fusion non-local block (ablation)ResNet-101 + fusion · Cityscapes valmIoU: 76.5 -> 77.3Improved
use AFNB instead of FNB (ablation)ResNet-101 + fusion · Cityscapes valmIoU: 77.3 -> 77.1No clear effect
add common fusion to non-local model (ablation)ResNet-101 + NB · Cityscapes valmIoU: 78.4 -> 79.0Improved
add AFNB to APNB model (ablation)ResNet-101 + APNB · Cityscapes valmIoU: 78.6 -> 79.9Improved
use pyramid average sampling instead of plain average sampling (ablation)APNB · Cityscapes valmIoU: 78.4 -> 79.3Improved
use average sampling instead of max sampling (ablation)APNB · Cityscapes valmIoU: 78.1 -> 78.4Improved
increase anchor points from 50 to 225 with pyramid sizes (1,4,8,12) (ablation)APNB · Cityscapes valmIoU: 79.3 -> 80.1Improved

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