Applying Eigencontours to PolarMask-Based Instance Segmentation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 13 references that are in the map. First posted on arXiv 24 Aug 2022.
Builds on
10 of 13 references.
References · 10
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2017Mask R-CNNcited by 7,277
- 2018Path Aggregation Network for Instance Segmentationcited by 798
- 2017Focal Loss for Dense Object Detectioncited by 752
- 2019Hybrid Task Cascade for Instance Segmentationcited by 481
- 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
- 2021Instances as Queriescited by 158
- 2019Explicit Shape Encoding for Real-Time Instance Segmentationcited by 41
- 2022Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximationcited by 10
Built on by
Not cited yet.