Region Proposal Rectification Towards Robust Instance Segmentation of Biological Images

TL;DR

This paper introduces a region proposal rectification module that enhances top-down instance segmentation in biological images by incorporating neighbor information, leading to more complete and accurate segmentation masks.

Contribution

The paper proposes a novel RPR module with a progressive ROIAlign and attentive FFN, improving segmentation accuracy by addressing over-crop issues in biological image analysis.

Findings

Significant improvement in region proposal correction

Enhanced segmentation performance on biological datasets

Effective in both anchor-based and anchor-free methods

Abstract

Top-down instance segmentation framework has shown its superiority in object detection compared to the bottom-up framework. While it is efficient in addressing over-segmentation, top-down instance segmentation suffers from over-crop problem. However, a complete segmentation mask is crucial for biological image analysis as it delivers important morphological properties such as shapes and volumes. In this paper, we propose a region proposal rectification (RPR) module to address this challenging incomplete segmentation problem. In particular, we offer a progressive ROIAlign module to introduce neighbor information into a series of ROIs gradually. The ROI features are fed into an attentive feed-forward network (FFN) for proposal box regression. With additional neighbor information, the proposed RPR module shows significant improvement in correction of region proposal locations and thereby exhibits favorable instance segmentation performances on three biological image datasets compared to state-of-the-art baseline methods. Experimental results demonstrate that the proposed RPR module is effective in both anchor-based and anchor-free top-down instance segmentation approaches, suggesting the proposed method can be applied to general top-down instance segmentation of biological images.