English

SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning

Computer Vision and Pattern Recognition 2023-10-02 v1

Abstract

Pre-training is a strong strategy for enhancing visual models to efficiently train them with a limited number of labeled images. In semantic segmentation, creating annotation masks requires an intensive amount of labor and time, and therefore, a large-scale pre-training dataset with semantic labels is quite difficult to construct. Moreover, what matters in semantic segmentation pre-training has not been fully investigated. In this paper, we propose the Segmentation Radial Contour DataBase (SegRCDB), which for the first time applies formula-driven supervised learning for semantic segmentation. SegRCDB enables pre-training for semantic segmentation without real images or any manual semantic labels. SegRCDB is based on insights about what is important in pre-training for semantic segmentation and allows efficient pre-training. Pre-training with SegRCDB achieved higher mIoU than the pre-training with COCO-Stuff for fine-tuning on ADE-20k and Cityscapes with the same number of training images. SegRCDB has a high potential to contribute to semantic segmentation pre-training and investigation by enabling the creation of large datasets without manual annotation. The SegRCDB dataset will be released under a license that allows research and commercial use. Code is available at: https://github.com/dahlian00/SegRCDB

Keywords

Cite

@article{arxiv.2309.17083,
  title  = {SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning},
  author = {Risa Shinoda and Ryo Hayamizu and Kodai Nakashima and Nakamasa Inoue and Rio Yokota and Hirokatsu Kataoka},
  journal= {arXiv preprint arXiv:2309.17083},
  year   = {2023}
}

Comments

ICCV2023. Code: https://github.com/dahlian00/SegRCDB, Project page: https://dahlian00.github.io/SegRCDBPage/

R2 v1 2026-06-28T12:35:52.711Z