AI Paper Atlas

Research map / Detection and segmentation / CNN features

ACFNet: Attentional Class Feature Network for Semantic Segmentation

Fan Zhang, Yanqin Chen, Zhihang Li, Zhibin Hong, Jingtuo Liu, Feifei Ma, Junyu Han, Errui Ding

ICCV 2019 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 326 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 class center concatenated with features (ablation)ResNet-101 · Cityscapes valmIoU: 75.85 -> 77.94Improved
add attentional class feature (sum) on top of class center (ablation)ResNet-101 · Cityscapes valmIoU: 77.94 -> 79.32Improved
use ACF(sum) instead of ACF(concat) (ablation)ResNet-101 + ACF · Cityscapes valmIoU: 79.17 -> 79.32No clear effect
add ACF module to ResNet-101 (fine output)ResNet-101 · Cityscapes valmIoU: 75.85 -> 79.32Improved
refine coarse to fine segmentation with ACFResNet-101 + ACF (sum) · Cityscapes valmIoU: 76.56 -> 79.32Improved
add ACF module after ASPPResNet-101 + ASPP · Cityscapes valmIoU: 78.42 -> 80.08Improved
add online bootstrappingResNet-101 + ASPP + ACF · Cityscapes valmIoU: 80.08 -> 80.99Improved
add multi-scale and flip testingResNet-101 + ASPP + ACF · Cityscapes valmIoU: 80.08 -> 81.46Improved
compare ACFNet with PSANet under train-fine only trainingACFNet · Cityscapes testmIoU: 78.6 -> 80.8Improved
compare ACFNet with DenseASPP using train-fine and val-fineACFNet · Cityscapes testmIoU: 80.6 -> 81.8Improved
compare ACFNet with DenseASPP on truck classACFNet · Cityscapes testtruck IoU: 78.0 -> 76.6Hurt

Later papers that compared with this method

4 later accepted papers report ACFNet as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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