Interactive Full Image Segmentation by Considering All Regions Jointly
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 cor...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.1812.01888 |