CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation. Ju, J., Noh, H., Wang, Y., Seo, M., & Choi, D. March, 2023. arXiv:2303.11606 [cs]
CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation [link]Paper  abstract   bibtex   
Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with pseudo-labeling pixels having high confidences for unlabeled images. However, using only highconfidence pixels for self-training may result in losing much of the information in the unlabeled datasets due to poor confidence calibration of modern deep learning networks. In this paper, we propose a class-adaptive semisupervision framework for semi-supervised semantic segmentation (CAFS) to cope with the loss of most information that occurs in existing high-confidence-based pseudolabeling methods. Unlike existing semi-supervised semantic segmentation frameworks, CAFS constructs a validation set on a labeled dataset, to leverage the calibration performance for each class. On this basis, we propose a calibration aware class-wise adaptive thresholding and classwise adaptive oversampling using the analysis results from the validation set. Our proposed CAFS achieves state-ofthe-art performance on the full data partition of the base PASCAL VOC 2012 dataset and on the 1/4 data partition of the Cityscapes dataset with significant margins of 83.0% and 80.4%, respectively. The code is available at https://github.com/cjf8899/CAFS.
@misc{ju_cafs_2023,
	title = {{CAFS}: {Class} {Adaptive} {Framework} for {Semi}-{Supervised} {Semantic} {Segmentation}},
	shorttitle = {{CAFS}},
	url = {http://arxiv.org/abs/2303.11606},
	abstract = {Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with pseudo-labeling pixels having high confidences for unlabeled images. However, using only highconfidence pixels for self-training may result in losing much of the information in the unlabeled datasets due to poor confidence calibration of modern deep learning networks. In this paper, we propose a class-adaptive semisupervision framework for semi-supervised semantic segmentation (CAFS) to cope with the loss of most information that occurs in existing high-confidence-based pseudolabeling methods. Unlike existing semi-supervised semantic segmentation frameworks, CAFS constructs a validation set on a labeled dataset, to leverage the calibration performance for each class. On this basis, we propose a calibration aware class-wise adaptive thresholding and classwise adaptive oversampling using the analysis results from the validation set. Our proposed CAFS achieves state-ofthe-art performance on the full data partition of the base PASCAL VOC 2012 dataset and on the 1/4 data partition of the Cityscapes dataset with significant margins of 83.0\% and 80.4\%, respectively. The code is available at https://github.com/cjf8899/CAFS.},
	urldate = {2023-05-10},
	publisher = {arXiv},
	author = {Ju, Jingi and Noh, Hyeoncheol and Wang, Yooseung and Seo, Minseok and Choi, Dong-Geol},
	month = mar,
	year = {2023},
	note = {arXiv:2303.11606 [cs]},
	keywords = {\#nosource, Computer Science - Computer Vision and Pattern Recognition},
}

Downloads: 0