SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning

TL;DR

SegRCDB introduces a formula-driven supervised learning approach for semantic segmentation pre-training, eliminating the need for manual annotations and outperforming traditional datasets like COCO-Stuff in key benchmarks.

Contribution

This paper presents the first application of formula-driven supervised learning for semantic segmentation pre-training, enabling large-scale dataset creation without manual labels.

Findings

SegRCDB pre-training outperforms COCO-Stuff on ADE-20k and Cityscapes.

Eliminates need for manual annotation in dataset creation.

Enhances efficiency in semantic segmentation pre-training.

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