Research map / Image generation / Fast diffusion sampling
A Gift From the Integration of Discriminative and Diffusion-Based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation
Hao Wang, Keyan Hu, Xin Guo, Haifeng Li, Chao Tao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add rough-label guidance to image-only conditioning (ablation) | IDGBR · Potsdam | WFm: 30.39 -> 40.34 | Improved |
| add rough-label guidance to image-only conditioning (ablation) | IDGBR · Potsdam | mIoU: 58.90 -> 80.88 | Improved |
| add rough-label guidance to image-only conditioning (ablation) | IDGBR · CHN6-CUG road | WFm: 33.66 -> 37.64 | Improved |
| add cubic timestep sampling (ablation) | IDGBR · Potsdam | WFm: 40.34 -> 42.59 | Improved |
| add cubic timestep sampling (ablation) | IDGBR · CHN6-CUG road | WFm: 37.64 -> 37.16 | Hurt |
| refine DINOv2 coarse masks with IDGBR | DINOv2 · FGFD farmland | WFm: 33.60 -> 46.73 | Improved |
| refine DINOv2 coarse masks with IDGBR | DINOv2 · CHN6-CUG road | WFm: 27.93 -> 34.65 | Improved |
| refine SegFormer masks with IDGBR | SegFormer · Potsdam | WFm: 39.71 -> 42.59 | Improved |
| refine SegFormer masks with IDGBR | SegFormer · Vaihingen | WFm: 43.76 -> 45.04 | Improved |
| refine DeepLabV3+ masks with IDGBR | DeepLabV3+ · Potsdam | mIoU: 83.53 -> 83.37 | No clear effect |
| refine LSK masks with IDGBR | LSK · WHU Building post-reconstruction | WFm: 70.81 -> 71.18 | No clear effect |
| IDGBR versus Mask2Former on boundary refinement | SegFormer + IDGBR · WHU Building post-disaster | WFm: 71.33 -> 75.91 | Improved |
Closest papers by meaning
- SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation (CVPR 2024 · similarity 0.91)
- Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation (AAAI 2025 · similarity 0.87)
- DiffusionSat: A Generative Foundation Model for Satellite Imagery (ICLR 2024 · similarity 0.87)
- ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object (CVPR 2025 · similarity 0.86)
- MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation (NeurIPS 2024 · similarity 0.86)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.86)
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.
