Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-Wise Memory Bank
Abstract
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach not only outperforms the current state-of-the-art for semi-supervised semantic segmentation but also for semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. Code is available at https://github.com/Shathe/SemiSeg-Contrastive
Cite
Text
Alonso et al. "Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-Wise Memory Bank." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00811Markdown
[Alonso et al. "Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-Wise Memory Bank." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/alonso2021iccv-semisupervised/) doi:10.1109/ICCV48922.2021.00811BibTeX
@inproceedings{alonso2021iccv-semisupervised,
title = {{Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-Wise Memory Bank}},
author = {Alonso, Iñigo and Sabater, Alberto and Ferstl, David and Montesano, Luis and Murillo, Ana C.},
booktitle = {International Conference on Computer Vision},
year = {2021},
pages = {8219-8228},
doi = {10.1109/ICCV48922.2021.00811},
url = {https://mlanthology.org/iccv/2021/alonso2021iccv-semisupervised/}
}