AI Paper Atlas

Research map / Detection and segmentation / CNN features

ExFuse: Enhancing Feature Fusion for Semantic Segmentation

Zhenli Zhang, Xiangyu Zhang, Chao Peng, Xiangyang Xue, Jian Sun

ECCV 2018 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 604 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 semantic supervision (ablation)GCN baseline (ResNeXt 101) · PASCAL VOC 2012 valmIoU: 76.0 -> 77.5Improved
add layer rearrangement {8,8,9,8} (ablation)GCN + SS · PASCAL VOC 2012 valmIoU: 77.5 -> 78.3Improved
add semantic embedding branch (ablation)GCN + SS + LR · PASCAL VOC 2012 valmIoU: 78.3 -> 79.0Improved
add explicit channel resolution embedding (ablation)GCN + SS + LR · PASCAL VOC 2012 valmIoU: 78.3 -> 78.8Improved
add densely adjacent prediction (ablation)GCN + SS + LR + SEB · PASCAL VOC 2012 valmIoU: 79.0 -> 79.6Improved
add more output channels without DAP (ablation)GCN + SS + LR + SEB · PASCAL VOC 2012 valmIoU: 79.0 -> 79.1No clear effect
add auxiliary segmentation loss on deconvolution output (ablation)GCN + SS + LR · PASCAL VOC 2012 valmIoU: 78.3 -> 78.2No clear effect
replace deconvolution with sub-pixel upsample without supervision (ablation)GCN + SS + LR · PASCAL VOC 2012 valmIoU: 78.3 -> 77.6Hurt
add semantic supervision (auxiliary losses in pretraining) (ablation)ResNet 50 · PASCAL VOC 2012 valmIoU: 72.4 -> 73.5Improved
add semantic supervision (auxiliary losses in pretraining) (ablation)ResNet 50 · ImageNet valtop-1 classification error: 24.15 -> 24.77Hurt
fuse low-level feature levels 1 and 2 into GCN (ablation)original GCN ResNeXt 101 · PASCAL VOC 2012 valmIoU: 75.98 -> 76.02No clear effect
fuse low-level feature levels 1 and 2 into ExFuse (ablation)ExFuse · PASCAL VOC 2012 valmIoU: 78.69 -> 80.04Improved

Later papers that compared with this method

2 later accepted papers report ExFuse as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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