Getting to 99% Accuracy in Interactive Segmentation

Understand

Interactive object cutout tools are the cornerstone of the image editing workflow.

• Recent deep-learning based interactive segmentation algorithms have made significant progress in handling complex images and rough binary selections can typically be obtained with just a few clicks.
• Yet, deep learning techniques tend to plateau once this rough selection has been reached.
• In this work, we interpret this plateau as the inability of current algorithms to sufficiently leverage each user interaction and also as the limitations of current training/testing datasets.