Applying Eigencontours to PolarMask-Based Instance Segmentation

2022/08/24 by Wonhui Park, Park, Wonhui, Dongkwon Jin +3
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Retrieval and Classification Techniques #Medical Image Segmentation Techniques

paper · pdf · doi:10.48550/arxiv.2208.11258

openalex publication_date 2022/08/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation
• PolarMask: Single Shot Instance Segmentation with Polar Representation
• PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond
• ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer
• E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation