AI Paper Atlas

Research map / Detection and segmentation / CNN features

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

Xiangtai Li, Xia Li, Li Zhang, Guangliang Cheng, Jianping Shi, Zhouchen Lin, Shaohua Tan, Yunhai Tong

ECCV 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 340 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 decoupled body/edge frameworkFCN ResNet-50 · Cityscapes valmIoU (%): 76.6 -> 80.1Improved
add decoupled body/edge frameworkFCN ResNet-101 · Cityscapes valmIoU (%): 77.8 -> 80.8Improved
add L_body supervision (ablation)FCN + BG & EP · Cityscapes valmIoU (%): 78.3 -> 78.8Improved
add L_bce alone (ablation)FCN + BG & EP · Cityscapes valmIoU (%): 78.3 -> 78.3No clear effect
add edge OHEM loss with L_bce (ablation)FCN + BG & EP · Cityscapes valmIoU (%): 78.3 -> 78.7Improved
add all three losses (ablation)FCN + BG & EP · Cityscapes valmIoU (%): 78.3 -> 80.1Improved
add low-level F_fine to edge module (ablation)ours · Cityscapes valmIoU (%): 79.3 -> 80.1Improved
add hard pixel mining on edge loss (ablation)ours · Cityscapes valmIoU (%): 79.0 -> 80.1Improved
add warping in body generation (ablation)FCN + BG & EP · Cityscapes valmIoU (%): 76.9 -> 78.3Improved
add encoder-decoder in body generation (ablation)FCN + BG & EP · Cityscapes valmIoU (%): 77.3 -> 78.3Improved
add edge preservation module (ablation)FCN + BG · Cityscapes valmIoU (%): 77.9 -> 78.3Improved
use our BG module instead of DCNFCN · Cityscapes valmIoU (%): 78.2 -> 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