Rethinking interactive image segmentation: Feature space 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 step back to propose simultaneous segment from multiple images guided by feature space projection. This strategy in stark contrast existing methodologies, which perform domain. show that achieves competitive results with state-of-the-art methods foreground datasets: iCoSeg, DAVIS, Rooftop. Moreover, semantic context, it 91.5% accuracy Cityscapes dataset, being 74.75 times faster than original procedure. Further, our contribution sheds light on novel direction can be integrated methodologies. The supplementary material presents video demonstrations. Code available at https://github.com/LIDS-UNICAMP/rethinking-interactive-image-segmentation.