We address interactive full image annotation, where the goal is to accurately
segment all object and stuff regions in an image. We propose an interactive,
scribble-based annotation framework which operates on the whole image to
produce segmentations for all regions. This enables sharing scribble
corrections across regions, and allows the annotator to focus on the largest
errors made by the machine across the whole image. To realize this, we adapt
Mask-RCNN into a fast interactive segmentation framework and introduce an
instance-aware loss measured at the pixel-level in the full image canvas, which
lets predictions for nearby regions properly compete for space. Finally, we
compare to interactive single object segmentation on the COCO panoptic dataset.
We demonstrate that our interactive full image segmentation approach leads to a
5% IoU gain, reaching 90% IoU at a budget of four extreme clicks and four
corrective scribbles per region.

研究提出了一种基于涂鸦的交互式全图像注释框架，将 Mask-RCNN 改进成快速交互式分割框架，并在完整的图像画布上引入像素级别的实例感知损失，实现注释者可将识别错误共享至整张图片中的所有区域并着重核查所有区域中机器产生的最大误差。通过在 COCO 全景数据集上进行实验，证明了该交互式完整图像分割方法实现了 5％的 IoU 增益，在每个区域四次极限点击和四次更正涂鸦的情况下达到了 90％的 IoU。