Research map / Detection and segmentation / CNN features
Progressive Semantic Segmentation
Chuong Huynh, Anh Tuan Tran, Khoa Luu, Minh Hoai
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 |
|---|---|---|---|
| Apply MagNet progressive refinement to the segmentation backbone | HRNetV2W18+OCR · Cityscapes | mIoU: 66.91% to 67.57% | Improved |
| Use progressive refinement rather than downsampling | MagNet · Inria Aerial | mIoU: 51.29 -> 87.01 | Improved |
| Use progressive refinement rather than patch processing | MagNet · Inria Aerial | mIoU: 86.04 -> 87.01 | Improved |
| Use progressive refinement rather than SegFix | MagNet · Cityscapes | mean Boundary Accuracy: 47.67% -> 49.52% | Improved |
| Use input size 1024×512 instead of 512×256 | HRNetV2W18+OCR · Cityscapes | mIoU: 65.03 -> 73.18 | Improved |
| Increase one-run input size from 512×256 to 1024×512 | HRNetV2W18+OCR · Cityscapes | memory: 3585 -> 9993 | Hurt |
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.
- SegFix — SegFix: Model-Agnostic Boundary Refinement for Segmentation (ECCV 2020) · better on 2 of 2 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
- MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation (CVPR 2024 · similarity 0.84)
- EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation (CVPR 2024 · similarity 0.84)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.84)
- FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning (NeurIPS 2025 · similarity 0.82)
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation (NeurIPS 2025 · similarity 0.82)
- OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation (NeurIPS 2025 · similarity 0.82)
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.
