Сравнение методов

	Трансформер зрения со слабой разметкой (WS-ViT)	Самообучение с учителем
Область	Глубокое обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2021–2022	2018–2020
Автор метода	Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and others	LeCun, Y. and community (formalized ~2018–2020)
Тип	Self-attention image model with weakly supervised training	Representation learning paradigm
Основополагающий источник	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR).	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/
Другие названия	WS-ViT, weakly supervised ViT, weak supervision with vision transformer, ViT with weak labels	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Связанные	4	3
Сводка	Weakly Supervised Vision Transformer (WS-ViT) trains a Vision Transformer on image data that lacks precise pixel-level annotations, instead using cheaper, noisier supervision such as image-level class tags, bounding boxes, or web-scraped text. The global self-attention mechanism of the transformer makes it especially capable of localising objects and learning discriminative features from these incomplete labels.	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.