Self-Supervised AutoFlow

Hsin-Ping Huang, Charles Herrmann, Junhwa Hur, Erika Lu, Kyle Sargent, Austin Stone, Ming-Hsuan Yang, Deqing Sun

CVPR 2023 pp. 11412-11421

doi:10.1109/CVPR52729.2023.01098 /cvpr/2023/huang2023cvpr-selfsupervised/

Abstract

Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric. Observing a strong correlation between the ground truth search metric and self-supervised losses, we introduce self-supervised AutoFlow to handle real-world videos without ground truth labels. Using self-supervised loss as the search metric, our self-supervised AutoFlow performs on par with AutoFlow on Sintel and KITTI where ground truth is available, and performs better on the real-world DAVIS dataset. We further explore using self-supervised AutoFlow in the (semi-)supervised setting and obtain competitive results against the state of the art.

PDF CVPR Semantic Scholar

Cite

Text

Huang et al. "Self-Supervised AutoFlow." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.01098

Markdown

[Huang et al. "Self-Supervised AutoFlow." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/huang2023cvpr-selfsupervised/) doi:10.1109/CVPR52729.2023.01098

BibTeX

@inproceedings{huang2023cvpr-selfsupervised,
  title     = {{Self-Supervised AutoFlow}},
  author    = {Huang, Hsin-Ping and Herrmann, Charles and Hur, Junhwa and Lu, Erika and Sargent, Kyle and Stone, Austin and Yang, Ming-Hsuan and Sun, Deqing},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {11412-11421},
  doi       = {10.1109/CVPR52729.2023.01098},
  url       = {https://mlanthology.org/cvpr/2023/huang2023cvpr-selfsupervised/}
}