SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation
Abstract
Instance segmentation is a problem of significance in computer vision. However, preparing annotated data for this task is extremely time-consuming and costly. By combining the advantages of 3D scanning, reasoning, and GAN-based domain adaptation techniques, we introduce a novel pipeline named SRDA to obtain large quantities of training samples with very minor effort. Our pipeline is well-suited to scenes that can be scanned, i.e. most indoor and some outdoor scenarios. To evaluate our performance, we build three representative scenes and a new dataset, with 3D models of various common objects categories and annotated real-world scene images. Extensive experiments show that our pipeline can achieve decent instance segmentation performance given very low human labor cost.
Cite
Text
Xu et al. "SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01258-8_8Markdown
[Xu et al. "SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/xu2018eccv-srda/) doi:10.1007/978-3-030-01258-8_8BibTeX
@inproceedings{xu2018eccv-srda,
title = {{SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation}},
author = {Xu, Wenqiang and Li, Yonglu and Lu, Cewu},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01258-8_8},
url = {https://mlanthology.org/eccv/2018/xu2018eccv-srda/}
}