Semi-Supervised Semantic Segmentation
Using Unreliable Pseudo-Labels

Yuchao Wang*	Haochen Wang*	Yujun Shen
Jingjing Fei	Wei Li	Guoqiang Jin
Liwei Wu	Rui Zhao	Xinyi Le

SenseTime Research Shanghai Jiao Tong University The Chinese University of Hong Kong

CVPR 2022

[Download Paper]

[Github Code]

The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability. We argue that every pixel matters to the model training, even its prediction is ambiguous. Intuitively, an unreliable prediction may get confused among the top classes (i.e., those with the highest probabilities), however, it should be confident about the pixel not belonging to the remaining classes. Hence, such a pixel can be convincingly treated as a negative sample to those most unlikely categories. Based on this insight, we develop an effective pipeline to make sufficient use of unlabeled data. Concretely, we separate reliable and unreliable pixels via the entropy of predictions, push each unreliable pixel to a category-wise queue that consists of negative samples, and manage to train the model with all candidate pixels. Considering the training evolution, where the prediction becomes more and more accurate, we adaptively adjust the threshold for the reliable-unreliable partition. Experimental results on various benchmarks and training settings demonstrate the superiority of our approach over the state-of-the-art alternatives.

Source Code

We have released the PyTorch based implementation for on the github page. Try our code!

[GitHub]

Paper

[Paper 5.5MB] [arXiv]

Citation

Citation

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels. In CVPR 2022.

[Bibtex]

@inproceedings{wang2022semi,
  title={Semi-Supervised Semantic Segmentation Using Unreliable Pseudo Labels},
  author={Wang, Yuchao and Wang, Haochen
    and Shen, Yujun and Fei, Jingjing
    and Li, Wei and Jin, Guoqiang
    and Wu, Liwei and Zhao, Rui and Le, Xinyi},
  booktitle={Proceedings of the IEEE/CVF International Conference on
    Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}