Research map / Detection and segmentation / Open-set and few-shot detection
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
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 SYNTHIA-Rand images to CamVid training data | T-Net · CamVid | per-class accuracy: 46.3 -> 56.5 ( 10.2) | Helped |
| Add SYNTHIA-Rand images to KITTI training data | T-Net · KITTI | per-class accuracy: 44.2 -> 51.6 ( 7.4) | Helped |
| Add SYNTHIA-Rand images to U-LabelMe training data | T-Net · U-LabelMe | per-class accuracy: 36.4 -> 46.7 ( 10.3) | Helped |
| Add SYNTHIA-Rand images to CBCL training data | T-Net · CBCL | per-class accuracy: 37.9 -> 48.4 ( 10.5) | Helped |
| Add SYNTHIA-Rand images to CamVid training data | FCN · CamVid | per-class accuracy: 52.8 -> 72.1 ( 18.3) | Helped |
| Add SYNTHIA-Rand images to KITTI training data | FCN · KITTI | per-class accuracy: 51.5 -> 59.4 ( 7.9) | Helped |
| Add SYNTHIA-Rand images to U-LabelMe training data | FCN · U-LabelMe | per-class accuracy: 60.1 -> 64.4 ( 4.3) | Helped |
| Add SYNTHIA-Rand images to CBCL training data | FCN · CBCL | per-class accuracy: 53.4 -> 53.5 ( 0.2) | Helped |
| Add SYNTHIA-Rand images to KITTI training data | FCN · KITTI | global accuracy: 82.3 -> 80.8 ( -1.5 ) | Hurt |
| Add SYNTHIA-Rand images to U-LabelMe training data | FCN · U-LabelMe | global accuracy: 79.4 -> 76.2 ( -3.2 ) | Hurt |
| Add SYNTHIA-Rand images to CBCL training data | FCN · CBCL | global accuracy: 79.7 -> 75.2 ( -4.5 ) | Hurt |
| Add SYNTHIA-Rand images to KITTI training data | T-Net · KITTI | global accuracy: 80.5 -> 80.8 ( 0.3) | Helped |
Closest papers by meaning
- ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes (CVPR 2018 · similarity 0.90)
- Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach (CVPR 2019 · similarity 0.89)
- Transferring and Regularizing Prediction for Semantic Segmentation (CVPR 2020 · similarity 0.88)
- Network-Free, Unsupervised Semantic Segmentation With Synthetic Images (CVPR 2023 · similarity 0.88)
- A Generative Approach at the Instance-Level for Image Segmentation Under Limited Training Data Conditions (Student Abstract) (AAAI 2025 · similarity 0.86)
- SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes (CVPR 2025 · 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.