Порівняння методів

	Самокероване сегментування екземплярів	Самокероване навчання
Галузь	Глибоке навчання	Машинне навчання
Родина	Machine learning	Machine learning
Рік появи	2021–2022	2018–2020
Автор методу	Wang et al. (FreeSOLO); Caron et al. (DINO)	LeCun, Y. and community (formalized ~2018–2020)
Тип	Self-supervised deep learning for pixel-level object delineation	Representation learning paradigm
Основоположне джерело	Wang, X., Zhu, Z., Cao, G., Yao, Z., Jiang, Z., & Ye, J. (2022). FreeSOLO: Learning to Segment Objects without Annotations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14176–14186.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
Інші назви	SSIS, unsupervised instance segmentation, label-free instance segmentation, self-supervised mask prediction	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Пов'язані	4	3
Підсумок	Self-supervised instance segmentation learns to detect and delineate individual object instances in images without any human-annotated masks or bounding boxes. Instead of relying on costly pixel-level labels, it exploits self-supervised pretraining, multi-view consistency, and pseudo-label generation to discover and segment objects purely from raw image data.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.