Combining self training and active learning for video segmentation

Alireza Fathi, Maria Florina Balcan, Xiaofeng Ren, James M. Rehg

Research output: Contribution to conferencePaperpeer-review


This work addresses the problem of segmenting an object of interest out of a video. We show that video object segmentation can be naturally cast as a semi-supervised learning problem and be efficiently solved using harmonic functions. We propose an incremental self-training approach by iteratively labeling the least uncertain frame and updating similarity metrics. Our self-training video segmentation produces superior results both qualitatively and quantitatively. Moreover, usage of harmonic functions naturally supports interactive segmentation. We suggest active learning methods for providing guidance to user on what to annotate in order to improve labeling efficiency. We present experimental results using a ground truth data set and a quantitative comparison to a representative object segmentation system.

Original languageEnglish (US)
StatePublished - 2011
Externally publishedYes
Event2011 22nd British Machine Vision Conference, BMVC 2011 - Dundee, United Kingdom
Duration: Aug 29 2011Sep 2 2011


Other2011 22nd British Machine Vision Conference, BMVC 2011
Country/TerritoryUnited Kingdom

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Combining self training and active learning for video segmentation'. Together they form a unique fingerprint.

Cite this