Rethinking Interactive Image Segmentation: Feature Space Annotation

TL;DR

This paper introduces a novel feature space projection approach for interactive image segmentation, enabling faster and more efficient annotation across multiple images, with competitive accuracy on benchmark datasets.

Contribution

It proposes a new feature space annotation method that outperforms existing image domain techniques in speed and maintains high segmentation accuracy.

Findings

Achieves 91.5% accuracy on Cityscapes dataset.

Is 74.75 times faster than traditional annotation methods.

Performs competitively on iCoSeg, DAVIS, and Rooftop datasets.

Abstract

Despite the progress of interactive image segmentation methods, high-quality pixel-level annotation is still time-consuming and laborious - a bottleneck for several deep learning applications. We take a step back to propose interactive and simultaneous segment annotation from multiple images guided by feature space projection. This strategy is in stark contrast to existing interactive segmentation methodologies, which perform annotation in the image domain. We show that feature space annotation achieves competitive results with state-of-the-art methods in foreground segmentation datasets: iCoSeg, DAVIS, and Rooftop. Moreover, in the semantic segmentation context, it achieves 91.5% accuracy in the Cityscapes dataset, being 74.75 times faster than the original annotation procedure. Further, our contribution sheds light on a novel direction for interactive image annotation that can be integrated with existing methodologies. The supplementary material presents video demonstrations. Code available at https://github.com/LIDS-UNICAMP/rethinking-interactive-image-segmentation.