ScholarGate
Assistant

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×
DomaineApprentissage profondApprentissage profond
FamilleMachine learningMachine learning
Année d'origine2018–20202020–2022
Auteur d'origineMultiple (Ouali et al., Zou et al., Chen et al.)Multiple groups (Caron et al.; Hamilton et al. among key contributors)
TypeSemi-supervised deep learning for pixel-level classificationSelf-supervised dense prediction
Source fondatriceOuali, 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 ↗
AliasSemi-SSL segmentation, pseudo-label segmentation, consistency regularization segmentation, label-efficient semantic segmentationSSL semantic segmentation, unsupervised semantic segmentation, label-free semantic segmentation, self-supervised dense prediction
Apparentées55
RésuméSemi-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
  1. v1
  2. 2 Sources
  3. PUBLISHED
  1. v1
  2. 2 Sources
  3. PUBLISHED

Aller à la recherche Télécharger les diapositives

ScholarGateComparer des méthodes: Semi-supervised Semantic Segmentation · Self-supervised Semantic Segmentation. Consulté le 2026-06-15 sur https://scholargate.app/fr/compare