Scribble-Supervised Target Extraction Method Based on Inner Structure-Constraint for Remote Sensing Images

TL;DR

This paper introduces a novel weakly supervised method for remote sensing target extraction using scribble annotations, employing inner structure-constraints to improve localization and boundary accuracy without auxiliary modules.

Contribution

The proposed method uniquely combines deformation consistency and active contour constraints to enhance scribble-based target extraction in remote sensing images.

Findings

Outperforms five state-of-the-art algorithms in experiments.

Effectively captures object structure with scribble supervision.

No auxiliary modules or prior cues needed.

Abstract

Weakly supervised learning based on scribble annotations in target extraction of remote sensing images has drawn much interest due to scribbles' flexibility in denoting winding objects and low cost of manually labeling. However, scribbles are too sparse to identify object structure and detailed information, bringing great challenges in target localization and boundary description. To alleviate these problems, in this paper, we construct two inner structure-constraints, a deformation consistency loss and a trainable active contour loss, together with a scribble-constraint to supervise the optimization of the encoder-decoder network without introducing any auxiliary module or extra operation based on prior cues. Comprehensive experiments demonstrate our method's superiority over five state-of-the-art algorithms in this field. Source code is available at https://github.com/yitongli123/ISC-TE.