Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Segmentation sémantique semi-supervisée× | Segmentation sémantique auto-supervisée× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2018–2020 | 2020–2022 |
| Auteur d'origine≠ | Multiple (Ouali et al., Zou et al., Chen et al.) | Multiple groups (Caron et al.; Hamilton et al. among key contributors) |
| Type≠ | Semi-supervised deep learning for pixel-level classification | Self-supervised dense prediction |
| Source fondatrice≠ | Ouali, Y., Hudelot, C., & Tami, M. (2020). Semi-Supervised Semantic Segmentation with Cross-Consistency Training. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12674–12684. DOI ↗ | Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660. DOI ↗ |
| Alias | Semi-SSL segmentation, pseudo-label segmentation, consistency regularization segmentation, label-efficient semantic segmentation | SSL semantic segmentation, unsupervised semantic segmentation, label-free semantic segmentation, self-supervised dense prediction |
| Apparentées | 5 | 5 |
| Résumé≠ | Semi-supervised semantic segmentation trains pixel-level labeling models using a small set of fully labeled images combined with a much larger set of unlabeled images. Techniques such as pseudo-labeling and consistency regularization extract supervisory signal from unlabeled data, making it possible to achieve near-fully-supervised accuracy at a fraction of the annotation cost. | Self-supervised semantic segmentation learns to assign a class label to every pixel of an image without relying on manually annotated segmentation masks. A backbone network is first trained on large quantities of unlabeled images using self-supervised objectives such as contrastive learning or masked image modeling, and the resulting dense features are then used to partition and label image regions, achieving competitive segmentation quality at a fraction of the annotation cost. |
| ScholarGateJeu de données ↗ |
|
|