BorderPointsMask: One-stage instance segmentation with boundary points representation

Hanqing Yang, Liyang Zheng, Saba Ghorbani Barzegar, Yu Zhang, Bin Xu

科研成果: 期刊稿件文章同行评审

15 引用 (Scopus)

摘要

The mechanism of human vision can easily detect and segment objects based on boundary information. Even though the deep learning instance segmentation model based on boundary information can mimic this human vision mechanism, its prospect is rarely explored. In this work, we propose a one-stage and anchor-free instance segmentation framework based on boundary points representation, named BorderPointsMask. The proposed BorderPointsMask doesn't need to rely on the object detector. It formulates instance segmentation as instance classification, boundary points location prediction, and boundary points attribute prediction. Furthermore, we design two effective approaches to improve the performance of this proposed framework. Specifically, we utilize the proposed BorderPoints Center-ness to suppress the predicted low-quality masks. And the Deformation Before-and-After Stacking Module (DBASM) is formulated to promote instance classification and boundary points learning. BorderPointsMask obtains 35.0% in mask Average Precision (AP) with single-model (ResNet-101-FPN) and single-scale training/testing on the COCO benchmark, which demonstrates the superior performance among one-stage frameworks. The code will be available.

源语言英语
页(从-至)348-359
页数12
期刊Neurocomputing
467
DOI
出版状态已出版 - 7 1月 2022

指纹

探究 'BorderPointsMask: One-stage instance segmentation with boundary points representation' 的科研主题。它们共同构成独一无二的指纹。

引用此