AI Paper Atlas

Research map / Detection and segmentation / CNN features

Class-wise Dynamic Graph Convolution for Semantic Segmentation

Hanzhe Hu, Deyi Ji, Weihao Gan, Shuai Bai, Wei Wu, Junjie Yan

ECCV 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 94 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
perform graph reasoning class-wise instead of over all pixels (plain GCN) (ablation)ResNet-101 + GCN · Cityscapes valmIoU (%): 78.2 -> 79.4Improved
add plain GCN to the ResNet-101 baseline (ablation)ResNet-101 · Cityscapes valmIoU (%): 76.3 -> 78.2Improved
add CDGC module to the ResNet-101 baseline (ablation)ResNet-101 · Cityscapes valmIoU (%): 76.3 -> 79.4Improved
add ASPP instead of CDGC to ResNet-101 (ablation)ResNet-101 · Cityscapes valmIoU (%): 76.3 -> 78.4Improved
add CDGC on top of ResNet-101 + ASPP (concat) (ablation)ResNet-101 + ASPP · Cityscapes valmIoU (%): 78.4 -> 80.0Improved
fuse refined feature by concatenation instead of summation (ablation)ResNet-101 + CDGC · Cityscapes valmIoU (%): 79.2 -> 79.4Improved
fuse refined feature by concatenation instead of summation (ablation)ResNet-101 + ASPP + CDGC · Cityscapes valmIoU (%): 79.9 -> 80.0Improved
replace similarity graph with dynamic sampling at easy-positive ratio 1.0 (ablation)ResNet-101 + ASPP + CDGC · Cityscapes valmIoU (%): 80.0 -> 81.1Improved
dynamic sampling with a low easy positive ratio of 0.2 vs similarity graph (ablation)ResNet-101 + ASPP + CDGC · Cityscapes valmIoU (%): 80.0 -> 79.8Hurt
increase easy positive sampling ratio from 0.2 to 1.0 (ablation)dynamic sampling CDGC · Cityscapes valmIoU (%): 79.8 -> 81.1Improved
add hard positive samples to easy positive (ablation)CDGC dynamic sampling · Cityscapes valmIoU (%): 79.9 -> 80.5Improved
add hard negative samples to easy positive (ablation)CDGC dynamic sampling · Cityscapes valmIoU (%): 79.9 -> 80.0No clear effect

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