# Object-Guided Instance Segmentation for Biological Images

arXiv: https://arxiv.org/abs/1911.09199 · HTML: https://mlsanity.com/paper/1911.09199/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 4 of 4)

- [PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond](https://mlsanity.com/paper/2105.02184/) (2021)
- [Region Proposal Rectification Towards Robust Instance Segmentation of Biological Images](https://mlsanity.com/paper/2203.02846/) (2022)
- [Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images](https://mlsanity.com/paper/2106.07159/) (2021)
- [SYNTA: A novel approach for deep learning-based image analysis in muscle histopathology using photo-realistic synthetic data](https://mlsanity.com/paper/2207.14650/) (2022)

## Abstract (arXiv)

Instance segmentation of biological images is essential for studying object behaviors and properties. The challenges, such as clustering, occlusion, and adhesion problems of the objects, make instance segmentation a non-trivial task. Current box-free instance segmentation methods typically rely on local pixel-level information. Due to a lack of global object view, these methods are prone to over- or under-segmentation. On the contrary, the box-based instance segmentation methods incorporate object detection into the segmentation, performing better in identifying the individual instances. In this paper, we propose a new box-based instance segmentation method. Mainly, we locate the object bounding boxes from their center points. The object features are subsequently reused in the segmentation branch as a guide to separate the clustered instances within an RoI patch. Along with the instance normalization, the model is able to recover the target object distribution and suppress the distribution of neighboring attached objects. Consequently, the proposed model performs excellently in segmenting the clustered objects while retaining the target object details. The proposed method achieves state-of-the-art performances on three biological datasets: cell nuclei, plant phenotyping dataset, and neural cells.