AI Paper Atlas

Research map / Detection and segmentation / CNN features

Object-Contextual Representations for Semantic Segmentation

Yuhui Yuan, Xilin Chen, Jingdong Wang

ECCV 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 1,310 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 supervision on the soft object regions (ablation)OCR (ResNet-101) · Cityscapes valmIoU: 77.31% -> 79.58%Improved
compute pixel-region relations from pixel and region representations instead of pixel only (DA scheme) (ablation)OCR · Cityscapes valmIoU: 79.01% -> 79.58%Improved
compute relations from pixel and region representations instead of an intermediate segmentation map (ACF scheme) (ablation)OCR · Cityscapes valmIoU: 78.02% -> 79.58%Improved
use OCR instead of PPMdilated ResNet-101 · Cityscapes test (w/o coarse)mIoU: 80.3% -> 81.8%Improved
use OCR instead of ASPPdilated ResNet-101 · Cityscapes test (w/o coarse)mIoU: 81.0% -> 81.8%Improved
use OCR instead of PPMdilated ResNet-101 · ADE20K valmIoU: 44.50% -> 45.28%Improved
use OCR instead of Self Attentiondilated ResNet-101 · LIP valmIoU: 55.15% -> 55.60%Improved
use OCR instead of Double Attentiondilated ResNet-101 · Cityscapes test (w/o coarse)mIoU: 81.2% -> 81.8%Improved
use HRNetV2-W48 backbone instead of ResNet-101 with OCROCR · Cityscapes test (w/o coarse)mIoU: 81.8% -> 82.4%Improved
apply PPM or ASPP on HRNet-W48 (ablation)HRNet-W48 · CityscapesmIoUHurt
add OCR to Panoptic-FPNPanoptic-FPN (ResNet-101) · COCO val 2017 panopticPQ: 43.0% -> 44.2%Improved
add OCR to Panoptic-FPNPanoptic-FPN (ResNet-50) · COCO val 2017 panopticPQ: 41.5 -> 42.7Improved

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