Research map / Detection and segmentation / Weakly supervised detection and segmentation
SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
Risa Shinoda, Ryo Hayamizu, Kodai Nakashima, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka
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 |
|---|---|---|---|
| pre-train with formula-driven SegRCDB instead of COCO-Stuff at same image count | Swin-B + UPerNet · ADE-20k | mIoU: 43.39 -> 43.85 | Improved |
| pre-train with SegRCDB instead of from scratch | Swin-B + UPerNet · Cityscapes | mIoU: 54.65 -> 73.06 | Improved |
| use ImageNet backbone pre-training instead of SegRCDB | Swin-B + UPerNet · ADE-20k | mIoU: 43.85 -> 46.37 | Improved |
| use grayscale instead of random class colors (ablation) | SegRCDB · ADE-20k | mIoU: 28.49 -> 34.05 | Improved |
| increase occlusion range r from 100 to 400 (ablation) | SegRCDB · ADE-20k | mIoU: 30.62 -> 34.12 | Improved |
| increase categories from 64 to 255, then to 500 (ablation) | SegRCDB · ADE-20k | mIoU: 31.67 -> 34.05 (255) -> 31.58 (500) | Mixed |
| increase number of images from 20k to 80k (ablation) | SegRCDB · ADE-20k | mIoU: 41.31 -> 42.25 | Improved |
| scale SegRCDB from 118k to 1M images (ablation) | SegRCDB · ADE-20k vs Cityscapes | mIoU: ADE-20k 43.85 -> 44.46; Cityscapes 73.06 -> 72.10 | Mixed |
| vary line width (1 to 3 px) and polygon count (ablation) | SegRCDB · ADE-20k | mIoU: 34.05 vs 34.03 (line width) | No clear effect |
| use Swin-B instead of ResNet-101 (ablation) | SegRCDB · Cityscapes | mIoU: 66.74 -> 70.23 | Improved |
| shift annotation vertices by 100 pixels (ablation) | SegRCDB · Cityscapes | mIoU: 70.23 -> 63.69 | Hurt |
| inflate polygons by 100 pixels (ablation) | SegRCDB · Cityscapes | mIoU: 70.23 -> 67.30 | Hurt |
Closest papers by meaning
- SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation (CVPR 2025 · similarity 0.86)
- SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search (ICML 2026 · similarity 0.86)
- Exploring Simple Open-Vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.86)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · similarity 0.86)
- SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation (NeurIPS 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.
