Self-Supervised Segmentation by Grouping Optical-Flow

Abstract

We propose to self-supervise a convolutional neural network operating on images using temporal information from videos. The task is to learn a representation of single images and the supervision for this is obtained by learning to group image pixels in such a way that their collective motion is “coherent”. This learning by grouping approach is used as a pre-training as well as segmentation strategy. Preliminary results suggest that the segments obtained are reasonable and the representation learned transfers well for classification.

Cite

Text

Mahendran et al. "Self-Supervised Segmentation by Grouping Optical-Flow." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11021-5_31

Markdown

[Mahendran et al. "Self-Supervised Segmentation by Grouping Optical-Flow." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/mahendran2018eccvw-selfsupervised/) doi:10.1007/978-3-030-11021-5_31

BibTeX

@inproceedings{mahendran2018eccvw-selfsupervised,
  title     = {{Self-Supervised Segmentation by Grouping Optical-Flow}},
  author    = {Mahendran, Aravindh and Thewlis, James and Vedaldi, Andrea},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {528-534},
  doi       = {10.1007/978-3-030-11021-5_31},
  url       = {https://mlanthology.org/eccvw/2018/mahendran2018eccvw-selfsupervised/}
}