手法を比較

	半教師ありインスタンスセグメンテーション	Self-supervised Vision Transformer
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2018–2021	2021–2022
提唱者	Multiple independent research groups (2018–2021)	Caron et al. (DINO); He et al. (MAE)
種類	Semi-supervised deep learning for dense prediction	Self-supervised pre-training for vision transformers
原典	Hu, H., Wei, P., Zheng, H., Bai, X., Wei, Y., & Chen, Y. (2021). Semi-supervised Semantic Segmentation via Adaptive Equalization Learning. Advances in Neural Information Processing Systems (NeurIPS), 34, 22106–22118.	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.
別名	Semi-supervised Mask R-CNN, pseudo-label instance segmentation, label-efficient instance segmentation, SSIS	SSL-ViT, self-supervised ViT, unsupervised ViT pre-training, vision transformer self-supervised pre-training
関連	6	4
概要	Semi-supervised instance segmentation trains a model to detect and delineate every object instance in an image using a small labeled set and a large unlabeled image corpus. By generating pseudo-labels from confident predictions on unlabeled images and enforcing consistency under augmentation, the approach achieves competitive mask accuracy at a fraction of the full annotation cost.	Self-supervised Vision Transformer (SSL-ViT) applies self-supervised pre-training objectives — such as masked patch prediction (MAE) or self-distillation with no labels (DINO) — to the Vision Transformer architecture, enabling powerful visual representations to be learned from large unlabeled image corpora before any task-specific fine-tuning.