LIP: Learning instance propagation for video object segmentation

Ye Lyu, G. Vosselman, Gui Song Xia, Michael Ying Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)
68 Downloads (Pure)


In recent years, the task of segmenting foreground objects from background in a video, i.e. video object segmentation (VOS), has received considerable attention. In this paper, we propose a single end-to-end trainable deep neural network, convolutional gated recurrent Mask-RCNN, for tackling the semi-supervised VOS task. We take advantage of both the instance segmentation network (Mask-RCNN) and the visual memory module (Conv-GRU) to tackle the VOS task. The instance segmentation network predicts masks for instances, while the visual memory module learns to selectively propagate information for multiple instances simultaneously, which handles the appearance change, the variation of scale and pose and the occlusions between objects. After offline and online training under purely instance segmentation losses, our approach is able to achieve satisfactory results without any post-processing or synthetic video data augmentation. Experimental results on DAVIS 2016 dataset and DAVIS 2017 dataset have demonstrated the effectiveness of our method for video object segmentation task.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
Number of pages10
ISBN (Electronic)9781728150239
Publication statusPublished - Oct 2019
Event17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019
Conference number: 17


Conference17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Abbreviated titleICCV 2019
Country/TerritoryKorea, Republic of
Internet address


  • Deep learning
  • Instance segmentation
  • Memory module
  • Video object segmentation


Dive into the research topics of 'LIP: Learning instance propagation for video object segmentation'. Together they form a unique fingerprint.

Cite this