Research map / Detection and segmentation / CNN features
Dual Super-Resolution Learning for Semantic Segmentation
Li Wang, Dong Li, Yousong Zhu, Lu Tian, Yi Shan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add SSSR to ESPNetv2 (ablation) | ESPNetv2 · CityScapes validation, 256×512 input | mIoU: 54.5 -> 55.7 | Improved |
| Add SISR branch to ESPNetv2 with SSSR (ablation) | ESPNetv2 + SSSR · CityScapes validation, 256×512 input | mIoU: 55.7 -> 56.9 | Improved |
| Add FA between SISR and SSSR (ablation) | ESPNetv2 + SSSR + SISR · CityScapes validation, 256×512 input | mIoU: 56.9 -> 59.5 | Improved |
| Add SSSR to DeepLabv3+ (ablation) | DeepLabv3+ · CityScapes validation, 256×512 input | mIoU: 56.5 -> 57.1 | Improved |
| Add SISR branch to DeepLabv3+ with SSSR (ablation) | DeepLabv3+ + SSSR · CityScapes validation, 256×512 input | mIoU: 57.1 -> 57.4 | Improved |
| Add FA between SISR and SSSR (ablation) | DeepLabv3+ + SSSR + SISR · CityScapes validation, 256×512 input | mIoU: 57.4 -> 59.2 | Improved |
| Add DSRL | ESPNetv2 · CityScapes validation | mIoU: 64.5 -> 66.9 | Improved |
| Add DSRL | DeepLabv3+ · CityScapes test | mIoU: 67.1 -> 69.3 | Improved |
| Add DSRL | ESPNetv2 · CamVid test | mIoU: 50.9 -> 54.4 | Improved |
| Add DSRL | DeepLabv3+ · CamVid test | mIoU: 60.4 -> 63.7 | Improved |
| Add DSRL | HRNet-w32 · MS COCO 2017 validation, 256×192 | mAP: 74.4 -> 75.6 | Improved |
| Add DSRL | HRNet-w32 · MS COCO 2017 validation, 160×128 | mAP: 69.2 -> 71.5 | Improved |
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.
- ESPNetv2 — ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation (ECCV 2018) · better on 3 of 3 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
- Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation (CVPR 2025 · similarity 0.88)
- SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning (NeurIPS 2025 · similarity 0.86)
- Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders (NeurIPS 2025 · similarity 0.85)
- SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (CVPR 2024 · similarity 0.85)
- MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation (CVPR 2024 · similarity 0.85)
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.85)
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.
