# Interactive Full Image Segmentation by Considering All Regions Jointly

## TL;DR

This paper introduces an interactive full image segmentation method that leverages shared scribble corrections across all regions, adapting Mask-RCNN for efficient, comprehensive annotation with improved accuracy and reduced annotation effort.

## Contribution

It presents a novel interactive segmentation framework that considers all image regions jointly, enabling efficient corrections and improved segmentation accuracy over existing methods.

## Key findings

- Achieves 90% IoU with four clicks and four scribbles per region.
- Provides a 5% IoU improvement over previous methods.
- Demonstrates effectiveness on COCO panoptic dataset.

## Abstract

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.