Cascaded Sparse Feature Propagation Network for Interactive Segmentation
This addresses the challenge of efficient and accurate interactive segmentation for users, though it appears incremental by improving on existing methods.
The paper tackles the problem of point-based interactive segmentation by proposing a cascade sparse feature propagation network to efficiently propagate user-provided annotations to unlabeled regions, resulting in more detailed object segmentation as validated on various benchmarks.
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}.