Delving into the cyclic mechanism in semi-supervised video object segmentation

Yuxi Li, Ning Xu, Jinlong Peng, John See, Weiyao Lin*

*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. By relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, we introduce a simple gradient correction module, which extends the offline pipeline to an online method while maintaining the efficiency of the former. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive experiments on challenging benchmarks of DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is beneficial to segmentation quality.
Original languageEnglish
Title of host publicationNIPS'20: Proceedings of the 34th International Conference on Neural Information Processing Systems
PublisherAssociation for Computing Machinery
Pages1218–1228
Number of pages11
ISBN (Print)9781713829546
DOIs
Publication statusPublished - Dec 2020
Event34th Conference on Neural Information Processing Systems 2020 - Virtual, Online
Duration: 6 Dec 202012 Dec 2020

Conference

Conference34th Conference on Neural Information Processing Systems 2020
Abbreviated titleNeurIPS 2020
CityVirtual, Online
Period6/12/2012/12/20

ASJC Scopus subject areas

  • Artificial Intelligence
  • Signal Processing

Fingerprint

Dive into the research topics of 'Delving into the cyclic mechanism in semi-supervised video object segmentation'. Together they form a unique fingerprint.

Cite this