Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
@article{Saleh2018EffectiveUO, title={Effective Use of Synthetic Data for Urban Scene Semantic Segmentation}, author={F. Saleh and M. S. Aliakbarian and M. Salzmann and L. Petersson and Jose M. Alvarez}, journal={ArXiv}, year={2018}, volume={abs/1807.06132} }
Training a deep network to perform semantic segmentation requires large amounts of labeled data. [...] Key Result Our experiments evidence the effectiveness of our approach on Cityscapes and CamVid with models trained on synthetic data only.Expand Abstract
Figures, Tables, and Topics from this paper
65 Citations
Spatially-Aware Domain Adaptation for Semantic Segmentation of Urban Scenes
- Computer Science
- 2019 IEEE International Conference on Image Processing (ICIP)
- 2019
- 1
Adapting Semantic Segmentation of Urban Scenes via Mask-Aware Gated Discriminator
- Computer Science
- 2019 IEEE International Conference on Multimedia and Expo (ICME)
- 2019
- 3
- Highly Influenced
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2020
- 32
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
- Computer Science
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 247
- PDF
Transferring and Regularizing Prediction for Semantic Segmentation
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 2
- PDF
Domain Adaptation With Foreground/Background Cues and Gated Discriminators
- Computer Science
- IEEE MultiMedia
- 2020
Restricted Deformable Convolution-Based Road Scene Semantic Segmentation Using Surround View Cameras
- Computer Science, Engineering
- IEEE Transactions on Intelligent Transportation Systems
- 2020
- 35
- Highly Influenced
- PDF
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
- Computer Science
- ArXiv
- 2020
- 2
- PDF
Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
- Computer Science
- ArXiv
- 2018
- 11
- PDF
References
SHOWING 1-10 OF 52 REFERENCES
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 899
- Highly Influential
- PDF
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes
- Computer Science
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 134
- Highly Influential
- PDF
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
- Computer Science
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 247
- Highly Influential
- PDF
The Cityscapes Dataset for Semantic Urban Scene Understanding
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 3,728
- Highly Influential
- PDF
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
- Computer Science
- ECCV
- 2016
- 92
- PDF
Bringing Background into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation
- Computer Science
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 21
- PDF
Exploiting Saliency for Object Segmentation from Image Level Labels
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 106
- PDF
Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2018
- 25
- PDF
Learning Hierarchical Features for Scene Labeling
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2013
- 2,153
- PDF
No More Discrimination: Cross City Adaptation of Road Scene Segmenters
- Computer Science
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 135
- PDF