Rethinking Interactive Image Segmentation: Feature Space Annotation
This addresses the annotation bottleneck for deep learning applications in computer vision, offering a novel direction that is faster than existing methods.
The paper tackles the problem of time-consuming pixel-level annotation for interactive image segmentation by proposing feature space annotation instead of image domain annotation, achieving 91.5% accuracy on Cityscapes while being 74.75 times faster than original annotation.
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.