ia-scribble-based-semi-weakly-supervised-learning

所属分类:人工智能/神经网络/深度学习
开发工具:Others
文件大小:0KB
下载次数:0
上传日期:2024-02-23 05:08:34
上 传 者sh-1993
说明:  FP4S:基于涂鸦的半弱监督学习的平面图图像分割
(FP4S: Floor plan image segmentation via scribble-based semi-weakly-supervised learning)

文件列表:
LICENSE

# FP4S-Floor-plan-image-segmentation-via-scribble-based-semi-weakly-supervised-learning FP4S: Floor plan image segmentation via scribble-based semi-weakly-supervised learning Official code and instructions for [**"Floor Plan Image Segmentation Via Scribble-Based Semi-Weakly Supervised Learning: A Style and Category-Agnostic Approach"**](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4727643) The paper has been submitted to **Automation in Construction** and is currently under peer review. The authors will make the annotated floor plan image datasets, the model code and the model weights of the best performance available for future research soon. ### Introduction This project introduces a scribble-based semi-weakly-supervised framework for floor plan image segmentation, merging weakly annotated and unlabeled images to boost model robustness and generalizability. This framework benefits from a simplified annotation process while retaining detailed information. Accordingly, we provide a new benchmark dataset for floor plan image parsing covering a wide range of architectural styles and categories. ### Dataset Coming soon... ### Acknowledgement The computational work for this research was performed on resources of the National Supercomputing Centre, Singapore (https://www.nscc.sg). The data sources used in this study are also gratefully acknowledged. This research was supported by the President's Graduate Fellowship of the National University of Singapore.

近期下载者

相关文件


收藏者