Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images

TL;DR

This paper introduces a novel object-guided instance segmentation approach for biological images, utilizing center point detection, a coarse-to-fine segmentation branch, and an auxiliary feature refinement module to improve accuracy in differentiating neighboring objects.

Contribution

The proposed method uniquely combines object center detection with an auxiliary feature refinement module for enhanced segmentation in biological images.

Findings

Outperforms existing methods on three biological datasets

Effectively differentiates neighboring objects with similar textures

Improves segmentation quality through feature refinement

Abstract

Instance segmentation is of great importance for many biological applications, such as study of neural cell interactions, plant phenotyping, and quantitatively measuring how cells react to drug treatment. In this paper, we propose a novel box-based instance segmentation method. Box-based instance segmentation methods capture objects via bounding boxes and then perform individual segmentation within each bounding box region. However, existing methods can hardly differentiate the target from its neighboring objects within the same bounding box region due to their similar textures and low-contrast boundaries. To deal with this problem, in this paper, we propose an object-guided instance segmentation method. Our method first detects the center points of the objects, from which the bounding box parameters are then predicted. To perform segmentation, an object-guided coarse-to-fine segmentation branch is built along with the detection branch. The segmentation branch reuses the object features as guidance to separate target object from the neighboring ones within the same bounding box region. To further improve the segmentation quality, we design an auxiliary feature refinement module that densely samples and refines point-wise features in the boundary regions. Experimental results on three biological image datasets demonstrate the advantages of our method. The code will be available at https://github.com/yijingru/ObjGuided-Instance-Segmentation.