Applying Eigencontours to PolarMask-Based Instance Segmentation

TL;DR

This paper introduces the integration of eigencontours, a data-driven contour descriptor, into the PolarMask network, resulting in improved instance segmentation performance on COCO2017 and SBD datasets.

Contribution

The novel contribution is the application of eigencontours to enhance PolarMask-based instance segmentation methods.

Findings

Improved segmentation accuracy over PolarMask on COCO2017.

Enhanced results on SBD dataset.

Qualitative analysis of eigencontours' characteristics.

Abstract

Eigencontours are the first data-driven contour descriptors based on singular value decomposition. Based on the implementation of ESE-Seg, eigencontours were applied to the instance segmentation task successfully. In this report, we incorporate eigencontours into the PolarMask network for instance segmentation. Experimental results demonstrate that the proposed algorithm yields better results than PolarMask on two instance segmentation datasets of COCO2017 and SBD. Also, we analyze the characteristics of eigencontours qualitatively. Our codes are available at https://github.com/dnjs3594/Eigencontours.