Contour-based Interactive Segmentation

TL;DR

This paper introduces a contour-based interactive segmentation method that reduces user interactions by replacing multiple clicks with a single contour, achieving comparable accuracy on standard benchmarks and a new challenging dataset.

Contribution

The paper presents a novel contour-based approach for interactive segmentation, demonstrating its effectiveness in reducing user interactions while maintaining accuracy.

Findings

Single contour achieves similar accuracy as multiple clicks.

Method performs well on standard benchmarks and challenging datasets.

Reduces user effort in image segmentation tasks.

Abstract

Recent advances in interactive segmentation (IS) allow speeding up and simplifying image editing and labeling greatly. The majority of modern IS approaches accept user input in the form of clicks. However, using clicks may require too many user interactions, especially when selecting small objects, minor parts of an object, or a group of objects of the same type. In this paper, we consider such a natural form of user interaction as a loose contour, and introduce a contour-based IS method. We evaluate the proposed method on the standard segmentation benchmarks, our novel UserContours dataset, and its subset UserContours-G containing difficult segmentation cases. Through experiments, we demonstrate that a single contour provides the same accuracy as multiple clicks, thus reducing the required amount of user interactions.