Cascade Sparse Feature Propagation Network for Interactive Segmentation
Chuyu Zhang (PLUS Lab, Shanghaitech University),* Hui Ren (ShanghaiTech), ChuanYang Hu (PLUS Lab, Shanghaitech University), Yongfei Liu (ShanghaiTech), Xuming He (ShanghaiTech University)
The 34th British Machine Vision Conference
Abstract
We aim to tackle the problem of point-based interactive segmentation, in which the key challenge is to propagate the user-provided annotations to unlabeled regions efficiently. Existing methods tackle this challenge by utilizing computationally expensive fully connected graphs or transformer architectures that sacrifice important detailed information necessary for accurate segmentation. To overcome these limitations, we propose a cascade sparse feature propagation network that selects the cleaned user-provided point information and propagates user-provided information to unlabeled regions. The sparse design of our network enables efficient information propagation on high-resolution features, resulting in more detailed object segmentation. We validate the effectiveness of our method through comprehensive experiments on various benchmarks, and the results demonstrate the superior performance of our approach.Citation
@inproceedings{Zhang_2023_BMVC,
author = {Chuyu Zhang and Hui Ren and ChuanYang Hu and Yongfei Liu and Xuming He},
title = {Cascade Sparse Feature Propagation Network for Interactive Segmentation},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0798.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by