Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

Xiaokang Chen, Yuhui Yuan, Gang Zeng, Jingdong Wang

CVPR 2021 pp. 2613-2622

doi:10.1109/CVPR46437.2021.00264 /cvpr/2021/chen2021cvpr-semisupervised/

Abstract

In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels.

PDF CVPR Semantic Scholar

Cite

Text

Chen et al. "Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00264

Markdown

[Chen et al. "Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/chen2021cvpr-semisupervised/) doi:10.1109/CVPR46437.2021.00264

BibTeX

@inproceedings{chen2021cvpr-semisupervised,
  title     = {{Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision}},
  author    = {Chen, Xiaokang and Yuan, Yuhui and Zeng, Gang and Wang, Jingdong},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {2613-2622},
  doi       = {10.1109/CVPR46437.2021.00264},
  url       = {https://mlanthology.org/cvpr/2021/chen2021cvpr-semisupervised/}
}