Research map / Detection and segmentation / Open-set and few-shot detection
Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 input-level adaptation using depth and semantic labels (ablation) | GIO-Ada · Virtual KITTI→KITTI | mIoU: 37.5 -> 45.9 | Helped |
| Add output-level adaptation with joint depth-semantic alignment (ablation) | GIO-Ada · Virtual KITTI→KITTI | mIoU: 37.5 -> 50.0 | Helped |
| Combine input- and output-level adaptation (ablation) | GIO-Ada · Virtual KITTI→KITTI | mIoU: 37.5 -> 53.5 | Helped |
| Add task-network guidance to image translation (ablation) | Input-level adaptation · Virtual KITTI→KITTI | mIoU: 39.8 -> 43.5 | Helped |
| Add depth as an image-transform input (ablation) | Input-level adaptation · Virtual KITTI→KITTI | mIoU: 43.5 -> 44.2 | Helped |
| Add semantic labels as an image-transform input (ablation) | Input-level adaptation · Virtual KITTI→KITTI | mIoU: 43.5 -> 44.7 | Helped |
| Add both depth and semantic labels as image-transform inputs (ablation) | Input-level adaptation · Virtual KITTI→KITTI | mIoU: 43.5 -> 45.9 | Helped |
| Align semantic outputs only (ablation) | Output-level adaptation · Virtual KITTI→KITTI | mIoU: 37.5 -> 45.9 | Helped |
| Align depth outputs only (ablation) | Output-level adaptation · Virtual KITTI→KITTI | mIoU: 37.5 -> 43.8 | Helped |
| Align depth and semantic outputs separately rather than jointly (ablation) | Output-level adaptation · Virtual KITTI→KITTI | mIoU: 37.5 -> 46.3 | Helped |
| Align joint depth-semantic output space instead of separate task spaces (ablation) | Output-level adaptation · Virtual KITTI→KITTI | mIoU: 46.3 -> 50.0 | Helped |
| Combine input- and output-level adaptation (ablation) | GIO-Ada · SYNTHIA→Cityscapes | mIoU: 23.3 -> 37.3 | Helped |
Closest papers by meaning
- Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation (CVPR 2018 · similarity 0.92)
- Network-Free, Unsupervised Semantic Segmentation With Synthetic Images (CVPR 2023 · similarity 0.91)
- Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection (CVPR 2019 · similarity 0.91)
- Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds (CVPR 2024 · similarity 0.89)
- Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation (NeurIPS 2026 · similarity 0.87)
- UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior (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.