Instance Segmentation of Dense and Overlapping Objects via Layering

TL;DR

This paper introduces a novel object layering approach for instance segmentation that effectively separates crowded and overlapping objects, outperforming previous methods on various biological datasets.

Contribution

The paper proposes a new layering technique for instance segmentation that handles complex overlaps without relying on shape or overlap assumptions.

Findings

Achieves competitive results on biological datasets

Not affected by complex object shapes or overlaps

Requires minimal post-processing

Abstract

Instance segmentation aims to delineate each individual object of interest in an image. State-of-the-art approaches achieve this goal by either partitioning semantic segmentations or refining coarse representations of detected objects. In this work, we propose a novel approach to solve the problem via object layering, i.e. by distributing crowded, even overlapping objects into different layers. By grouping spatially separated objects in the same layer, instances can be effortlessly isolated by extracting connected components in each layer. In comparison to previous methods, our approach is not affected by complex object shapes or object overlaps. With minimal post-processing, our method yields very competitive results on a diverse line of datasets: C. elegans (BBBC), Overlapping Cervical Cells (OCC) and cultured neuroblastoma cells (CCDB). The source code is publicly available.