arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.05145cs.CV
收藏

用于交互式分割的级联稀疏特征传播网络

Cascaded Sparse Feature Propagation Network for Interactive Segmentation

ShanghaiTech University(上海科技大学);Lingang Laboratory(临港实验室)

Chuyu Zhang, Chuanyang Hu, Hui Ren, Yongfei Liu, Xuming He

AI总结:

针对基于点的交互式分割中标注传播效率低和细粒度信息丢失问题,本文提出级联稀疏特征传播网络CSFPN,通过点击增强特征表示在高分辨率特征上高效传播信息,在多个基准上取得优越分割性能。

摘要:

我们旨在解决基于点的交互式分割问题,其关键挑战在于如何高效地将用户提供的标注传播到未标记区域。现有方法通过使用计算开销高昂的全连接图或Transformer架构来应对这一挑战,但这些方法牺牲了精确分割所需的重要细粒度信息。为克服这些局限性,我们提出了一种级联稀疏特征传播网络,该网络学习一种点击增强的特征表示,用于将用户提供的信息传播到未标记区域。我们网络的稀疏设计使得信息能够在高分辨率特征上高效传播,从而实现更精细的目标分割。我们通过在多个基准上的全面实验验证了所提方法的有效性,结果表明我们的方法具有优越的性能。代码可在 https://github.com/kleinzcy/CSFPN 获取。

英文摘要:

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 fine-grained information required for accurate segmentation. To overcome these limitations, we propose a cascade sparse feature propagation network that learns a click-augmented feature representation for propagating 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. Code is available at \href{https://github.com/kleinzcy/CSFPN}{https://github.com/kleinzcy/CSFPN}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑