ML Anthology

Unsupervised Moving Object Detection via Contextual Information Separation

Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto
CVPR 2019
doi:10.1109/CVPR.2019.00097 /cvpr/2019/yang2019cvpr-unsupervised/

Abstract

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms several methods that are pre-trained on large annotated datasets. Our model can be thought of as a generalization of classical variational generative region-based segmentation, but in a way that avoids explicit regularization or solution of partial differential equations at run-time.

PDF CVPR Semantic Scholar

Cite

Text

Yang et al. "Unsupervised Moving Object Detection via Contextual Information Separation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00097

Markdown

[Yang et al. "Unsupervised Moving Object Detection via Contextual Information Separation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/yang2019cvpr-unsupervised/) doi:10.1109/CVPR.2019.00097

BibTeX

@inproceedings{yang2019cvpr-unsupervised,
  title     = {{Unsupervised Moving Object Detection via Contextual Information Separation}},
  author    = {Yang, Yanchao and Loquercio, Antonio and Scaramuzza, Davide and Soatto, Stefano},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00097},
  url       = {https://mlanthology.org/cvpr/2019/yang2019cvpr-unsupervised/}
}