AI Paper Atlas

Research map / Detection and segmentation / CNN features

Dual Super-Resolution Learning for Semantic Segmentation

Li Wang, Dong Li, Yousong Zhu, Lu Tian, Yi Shan

CVPR 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 236 citations (OpenAlex)

Check 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 SSSR to ESPNetv2 (ablation)ESPNetv2 · CityScapes validation, 256×512 inputmIoU: 54.5 -> 55.7Improved
Add SISR branch to ESPNetv2 with SSSR (ablation)ESPNetv2 + SSSR · CityScapes validation, 256×512 inputmIoU: 55.7 -> 56.9Improved
Add FA between SISR and SSSR (ablation)ESPNetv2 + SSSR + SISR · CityScapes validation, 256×512 inputmIoU: 56.9 -> 59.5Improved
Add SSSR to DeepLabv3+ (ablation)DeepLabv3+ · CityScapes validation, 256×512 inputmIoU: 56.5 -> 57.1Improved
Add SISR branch to DeepLabv3+ with SSSR (ablation)DeepLabv3+ + SSSR · CityScapes validation, 256×512 inputmIoU: 57.1 -> 57.4Improved
Add FA between SISR and SSSR (ablation)DeepLabv3+ + SSSR + SISR · CityScapes validation, 256×512 inputmIoU: 57.4 -> 59.2Improved
Add DSRLESPNetv2 · CityScapes validationmIoU: 64.5 -> 66.9Improved
Add DSRLDeepLabv3+ · CityScapes testmIoU: 67.1 -> 69.3Improved
Add DSRLESPNetv2 · CamVid testmIoU: 50.9 -> 54.4Improved
Add DSRLDeepLabv3+ · CamVid testmIoU: 60.4 -> 63.7Improved
Add DSRLHRNet-w32 · MS COCO 2017 validation, 256×192mAP: 74.4 -> 75.6Improved
Add DSRLHRNet-w32 · MS COCO 2017 validation, 160×128mAP: 69.2 -> 71.5Improved

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