MaskPlus: Improving mask generation for instance segmentation

Shichao Xu, Shuyue Lan, Qi Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Instance segmentation is a promising yet challenging topic in computer vision. Recent approaches such as Mask R-CNN typically divide this problem into two parts - a detection component and a mask generation branch, and mostly focus on the improvement of the detection part. In this paper, we present an approach that extends Mask R-CNN with five novel techniques for improving the mask generation branch and reducing the conflicts between the mask branch and the detection component in training. These five techniques are independent to each other and can be flexibly utilized in building various instance segmentation architectures for increasing the overall accuracy. We demonstrate the effectiveness of our approach with tests on the COCO dataset.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2019-2027
Number of pages9
ISBN (Electronic)9781728165530
DOIs
StatePublished - Mar 2020
Event2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, United States
Duration: Mar 1 2020Mar 5 2020

Publication series

NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Conference

Conference2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
Country/TerritoryUnited States
CitySnowmass Village
Period3/1/203/5/20

Funding

We gratefully acknowledge the support from the US National Science Foundation awards 1724341 and 1834701.

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'MaskPlus: Improving mask generation for instance segmentation'. Together they form a unique fingerprint.

Cite this